{"object":"list","data":[{"id":"arkanecloud/moonshotai/Kimi-K3.1-Pro","object":"model","created":1793900129,"owned_by":"arkanecloud","model_name":"moonshotai/Kimi-K3.1-Pro","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/zai-org/GLM-5.3-Flash","object":"model","created":1793900129,"owned_by":"arkanecloud","model_name":"zai-org/GLM-5.3-Flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"tensorx/moonshotai/kimi-k3.1-pro","object":"model","created":1793855556,"owned_by":"tensorx","model_name":"moonshotai/kimi-k3.1-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":"Served by TensorX at mxfp4 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gemini-3-6-flash","object":"model","created":1793739015,"owned_by":"databricks","model_name":"databricks-gemini-3-6-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.6 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.499996e-7,"output_cost_per_token":3.7499994e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000053571,"cache_read_input_token_cost":7.499996e-8,"cache_creation_input_token_cost":7.4998e-7,"cache_creation_input_token_cost_priority":1.35002e-6},"list_pricing":{"input_cost_per_token":7.499996e-7,"output_cost_per_token":3.7499994e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000053571,"cache_read_input_token_cost":7.499996e-8,"cache_creation_input_token_cost":7.4998e-7,"cache_creation_input_token_cost_priority":1.35002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"arkanecloud/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1793250768,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/deepseek-ai/DeepSeek-V4-Flash-0731","object":"model","created":1793250768,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"databricks/databricks-gpt-6-1-terra","object":"model","created":1793060038,"owned_by":"databricks","model_name":"databricks-gpt-6-1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-6.1 Terra is an OpenAI model that advances the cost-intelligence frontier. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.9999998e-7,"output_cost_per_token":4.99999997e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":9.9999998e-8,"cache_creation_input_token_cost":1.24999e-6,"input_cost_per_token_above_272k_tokens":1.99997e-6,"output_cost_per_token_above_272k_tokens":7.50001e-6,"cache_creation_input_token_cost_priority":2.49998e-6,"cache_read_input_token_cost_above_272k_tokens":1.0003e-7,"input_cost_per_token_above_272k_tokens_priority":4.00001e-6,"output_cost_per_token_above_272k_tokens_priority":0.00001500002,"cache_creation_input_token_cost_above_272k_tokens":2.49998e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.9999e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5.00003e-6},"list_pricing":{"input_cost_per_token":9.9999998e-7,"output_cost_per_token":4.99999997e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":9.9999998e-8,"cache_creation_input_token_cost":1.24999e-6,"input_cost_per_token_above_272k_tokens":1.99997e-6,"output_cost_per_token_above_272k_tokens":7.50001e-6,"cache_creation_input_token_cost_priority":2.49998e-6,"cache_read_input_token_cost_above_272k_tokens":1.0003e-7,"input_cost_per_token_above_272k_tokens_priority":4.00001e-6,"output_cost_per_token_above_272k_tokens_priority":0.00001500002,"cache_creation_input_token_cost_above_272k_tokens":2.49998e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.9999e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5.00003e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6.1-terra","object":"model","created":1793045891,"owned_by":"azure","model_name":"gpt-6.1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.","source":null,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":6e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.5e-6,"input_cost_per_token_above_272k_tokens":2.4e-6,"output_cost_per_token_above_272k_tokens":9e-6,"cache_read_input_token_cost_above_272k_tokens":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens":3e-6},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":6e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.5e-6,"input_cost_per_token_above_272k_tokens":2.4e-6,"output_cost_per_token_above_272k_tokens":9e-6,"cache_read_input_token_cost_above_272k_tokens":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens":3e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/minimax/minimax-m3.1-flash","object":"model","created":1792854448,"owned_by":"tensorx","model_name":"minimax/minimax-m3.1-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"arkanecloud/deepseek-ai/DeepSeek-V3.2","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V3.2","context_length":163840,"max_input_tokens":null,"max_output_tokens":65536,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/deepseek-ai/DeepSeek-V4.1-Flash","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4.1-Flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/deepseek-ai/DeepSeek-V4-Flash","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4-Flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/deepseek-ai/DeepSeek-V4-Pro","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4-Pro","context_length":1000000,"max_input_tokens":null,"max_output_tokens":384000,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7e-6,"output_cost_per_token":3.4e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.7e-6,"output_cost_per_token":3.4e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/gemma4-26b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"gemma4-26b","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":1e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":1e-7,"cache_read_input_token_cost":5e-8},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/gemma4-31b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"gemma4-31b","context_length":131072,"max_input_tokens":null,"max_output_tokens":65536,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/gemma4-4b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"gemma4-4b","context_length":131072,"max_input_tokens":null,"max_output_tokens":65536,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":5e-8,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":5e-8,"cache_read_input_token_cost":5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/MiniMaxAI/MiniMax-M2.5","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"MiniMaxAI/MiniMax-M2.5","context_length":196000,"max_input_tokens":null,"max_output_tokens":98000,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/MiniMaxAI/MiniMax-M3","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"MiniMaxAI/MiniMax-M3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/ministral-14b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"ministral-14b","context_length":32768,"max_input_tokens":null,"max_output_tokens":16384,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/ministral-8b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"ministral-8b","context_length":131072,"max_input_tokens":null,"max_output_tokens":65536,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/mistralai/Mistral-Medium-3.5-128B","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"mistralai/Mistral-Medium-3.5-128B","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":3e-7},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/mistralai/Mistral-Small-4-119B-2603","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"mistralai/Mistral-Small-4-119B-2603","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/moonshotai/Kimi-K3","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"moonshotai/Kimi-K3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/nvidia/nemotron-3-super-120b-a12b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"nvidia/nemotron-3-super-120b-a12b","context_length":256000,"max_input_tokens":null,"max_output_tokens":16384,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":8e-7,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":8e-7,"cache_read_input_token_cost":1e-7},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/nvidia/nemotron-3-ultra-550b-a55b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"nvidia/nemotron-3-ultra-550b-a55b","context_length":512288,"max_input_tokens":null,"max_output_tokens":256144,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/openai/gpt-oss-120b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"openai/gpt-oss-120b","context_length":131072,"max_input_tokens":null,"max_output_tokens":65536,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/qwen38-27b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"qwen38-27b","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/qwen38-27b-turbo-v2","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"qwen38-27b-turbo-v2","context_length":150000,"max_input_tokens":null,"max_output_tokens":75000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":4e-8},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":4e-8},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/Qwen/Qwen3-235B-A22B-Instruct-2507","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"Qwen/Qwen3-235B-A22B-Instruct-2507","context_length":262000,"max_input_tokens":null,"max_output_tokens":16384,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/Qwen/Qwen3.6-35B-A3B","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"Qwen/Qwen3.6-35B-A3B","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-7},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/zai-org/GLM-5.2","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"zai-org/GLM-5.2","context_length":200000,"max_input_tokens":null,"max_output_tokens":100000,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":4.2e-6,"cache_read_input_token_cost":2.5e-7},"list_pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":4.2e-6,"cache_read_input_token_cost":2.5e-7},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/zai-org/GLM-5.3","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"zai-org/GLM-5.3","context_length":200000,"max_input_tokens":null,"max_output_tokens":100000,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":3e-7},"discount":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/zai-glm-5-3-flash","object":"model","created":1792693170,"owned_by":"mistral","model_name":"zai-glm-5-3-flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":3.3e-8},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":3.3e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"sference/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1792636080,"owned_by":"sference","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"sference/deepseek-ai/DeepSeek-V4-Flash-0731","object":"model","created":1792636080,"owned_by":"sference","model_name":"deepseek-ai/DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.8e-7,"output_cost_per_token":5.6e-7,"cache_read_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":2.8e-7,"output_cost_per_token":5.6e-7,"cache_read_input_token_cost":7e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"sference/moonshotai/Kimi-K3","object":"model","created":1792636080,"owned_by":"sference","model_name":"moonshotai/Kimi-K3","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":4.5e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":4.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"sference/zai-org/GLM-5.3","object":"model","created":1792636080,"owned_by":"sference","model_name":"zai-org/GLM-5.3","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4.2e-6,"cache_read_input_token_cost":2.6e-7},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4.2e-6,"cache_read_input_token_cost":2.6e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"sference/zai-org/GLM-5.3-Flash","object":"model","created":1792636080,"owned_by":"sference","model_name":"zai-org/GLM-5.3-Flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"meta/muse-spark-1.1","object":"model","created":1792552674,"owned_by":"meta","model_name":"muse-spark-1.1","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"meta/muse-spark-1.2","object":"model","created":1792552674,"owned_by":"meta","model_name":"muse-spark-1.2","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"meta/muse-spark-1.3","object":"model","created":1792552674,"owned_by":"meta","model_name":"muse-spark-1.3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"meta/muse-wonder-1.0","object":"model","created":1792552674,"owned_by":"meta","model_name":"muse-wonder-1.0","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4.1-flash-1017","object":"model","created":1792300420,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4.1-flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.25e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/deepseek-v4-1-flash-1017","object":"model","created":1792225624,"owned_by":"mistral","model_name":"deepseek-v4-1-flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":7.700000000000001e-9,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":6.6e-7,"cache_read_input_token_cost_batches":3.8500000000000006e-9},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":7.700000000000001e-9,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":6.6e-7,"cache_read_input_token_cost_batches":3.8500000000000006e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"vertex/deepseek-ai/deepseek-v4.1-flash-maas","object":"model","created":1792186462,"owned_by":"vertex","model_name":"deepseek-ai/deepseek-v4.1-flash-maas","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":3.3e-8},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":3.3e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-claude-haiku-5-5","object":"model","created":1791954861,"owned_by":"databricks","model_name":"databricks-claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Haiku 5.5 is Anthropic's fastest model in the Claude 5.5 family, optimized for high-volume, speed-sensitive workloads. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.999997e-8,"output_cost_per_token":4.9999999e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":9.999997e-9,"cache_creation_input_token_cost":1.2502e-7,"input_cost_per_token_above_100k_tokens":5.0001e-7,"output_cost_per_token_above_100k_tokens":2.49998e-6,"cache_creation_input_token_cost_above_1hr":1.9999e-7,"cache_read_input_token_cost_above_100k_tokens":4.998e-8,"cache_creation_input_token_cost_above_100k_tokens":6.2503e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.00002e-6},"list_pricing":{"input_cost_per_token":9.999997e-8,"output_cost_per_token":4.9999999e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":9.999997e-9,"cache_creation_input_token_cost":1.2502e-7,"input_cost_per_token_above_100k_tokens":5.0001e-7,"output_cost_per_token_above_100k_tokens":2.49998e-6,"cache_creation_input_token_cost_above_1hr":1.9999e-7,"cache_read_input_token_cost_above_100k_tokens":4.998e-8,"cache_creation_input_token_cost_above_100k_tokens":6.2503e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.00002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-4-argon","object":"model","created":1791907477,"owned_by":"vertex","model_name":"gemini-4-argon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.875e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1e-7,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_audio_token":4e-6,"input_cost_per_image_token":4e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.00002,"cache_read_input_audio_token_cost":2e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/deepseek-v4.1-flash","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"deepseek-v4.1-flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":393216,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.4624586978518405e-7,"output_cost_per_token":1.2312293489259202e-6,"cache_read_input_token_cost":1.2312293489259203e-8},"list_pricing":{"input_cost_per_token":2.4624586978518405e-7,"output_cost_per_token":1.2312293489259202e-6,"cache_read_input_token_cost":1.2312293489259203e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/deepseek-v4-flash-0731","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"deepseek-v4-flash-0731","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5670191713602622e-7,"output_cost_per_token":3.9175479284006554e-7,"cache_read_input_token_cost":4.477197632457892e-8},"list_pricing":{"input_cost_per_token":1.5670191713602622e-7,"output_cost_per_token":3.9175479284006554e-7,"cache_read_input_token_cost":4.477197632457892e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/gemma4","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"gemma4","context_length":256000,"max_input_tokens":null,"max_output_tokens":32000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.596497040572364e-7,"output_cost_per_token":1.6789491121717095e-6},"list_pricing":{"input_cost_per_token":5.596497040572364e-7,"output_cost_per_token":1.6789491121717095e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.2","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2","context_length":1000000,"max_input_tokens":null,"max_output_tokens":131072,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"list_pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.2-caveman","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-caveman","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"list_pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.2-caveman-lite","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-caveman-lite","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"list_pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.2-caveman-ultra","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-caveman-ultra","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"list_pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.2-honey","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-honey","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"list_pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.2-honey-lite","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-honey-lite","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"list_pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.2-honey-ultra","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-honey-ultra","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"list_pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.2-ponytail","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-ponytail","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"list_pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.2-ponytail-lite","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-ponytail-lite","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"list_pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.2-ponytail-ultra","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-ponytail-ultra","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"list_pricing":{"input_cost_per_token":1.7349140825774331e-6,"output_cost_per_token":5.1487772773265755e-6,"cache_read_input_token_cost":4.477197632457892e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.3","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":131072,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2312293489259202e-6,"output_cost_per_token":4.924917395703681e-6,"cache_read_input_token_cost":3.0780733723148005e-7},"list_pricing":{"input_cost_per_token":1.2312293489259202e-6,"output_cost_per_token":4.924917395703681e-6,"cache_read_input_token_cost":3.0780733723148005e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.3-flash","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.3-flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":131072,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2312293489259203e-7,"output_cost_per_token":4.924917395703681e-7,"cache_read_input_token_cost":2.4624586978518405e-8},"list_pricing":{"input_cost_per_token":1.2312293489259203e-7,"output_cost_per_token":4.924917395703681e-7,"cache_read_input_token_cost":2.4624586978518405e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/gpt-oss-120b","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"gpt-oss-120b","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.238598816228946e-7,"output_cost_per_token":7.835095856801311e-7},"list_pricing":{"input_cost_per_token":2.238598816228946e-7,"output_cost_per_token":7.835095856801311e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/kimi-k2.6","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"kimi-k2.6","context_length":256000,"max_input_tokens":null,"max_output_tokens":null,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.387376093555522e-7,"output_cost_per_token":4.1973727804292735e-6,"cache_read_input_token_cost":2.4624586978518405e-7},"list_pricing":{"input_cost_per_token":7.387376093555522e-7,"output_cost_per_token":4.1973727804292735e-6,"cache_read_input_token_cost":2.4624586978518405e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/kimi-k2.7-code","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"kimi-k2.7-code","context_length":256000,"max_input_tokens":null,"max_output_tokens":null,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.618605442481442e-7,"output_cost_per_token":4.309302721240721e-6,"cache_read_input_token_cost":2.2162128280666565e-7},"list_pricing":{"input_cost_per_token":8.618605442481442e-7,"output_cost_per_token":4.309302721240721e-6,"cache_read_input_token_cost":2.2162128280666565e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/kimi-k3","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"kimi-k3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.693688046777761e-6,"output_cost_per_token":0.000018468440233888806,"cache_read_input_token_cost":9.234220116944402e-7},"list_pricing":{"input_cost_per_token":3.693688046777761e-6,"output_cost_per_token":0.000018468440233888806,"cache_read_input_token_cost":9.234220116944402e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/llama-3.3-70b-instruct","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"llama-3.3-70b-instruct","context_length":128000,"max_input_tokens":null,"max_output_tokens":16000,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2312293489259202e-6,"output_cost_per_token":1.2312293489259202e-6},"list_pricing":{"input_cost_per_token":1.2312293489259202e-6,"output_cost_per_token":1.2312293489259202e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/minimax-m2.5","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"minimax-m2.5","context_length":1000000,"max_input_tokens":null,"max_output_tokens":64000,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.924917395703681e-7,"output_cost_per_token":2.4624586978518404e-6,"cache_read_input_token_cost":1.2312293489259203e-7},"list_pricing":{"input_cost_per_token":4.924917395703681e-7,"output_cost_per_token":2.4624586978518404e-6,"cache_read_input_token_cost":1.2312293489259203e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/minimax-m3","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"minimax-m3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":64000,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.924917395703681e-7,"output_cost_per_token":2.4624586978518404e-6,"cache_read_input_token_cost":1.2312293489259203e-7},"list_pricing":{"input_cost_per_token":4.924917395703681e-7,"output_cost_per_token":2.4624586978518404e-6,"cache_read_input_token_cost":1.2312293489259203e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/mistral-medium-3.5-128b","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"mistral-medium-3.5-128b","context_length":180000,"max_input_tokens":null,"max_output_tokens":16000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.014738934606051e-6,"output_cost_per_token":0.000010073694673030257},"list_pricing":{"input_cost_per_token":2.014738934606051e-6,"output_cost_per_token":0.000010073694673030257},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/mistral-small-3.2-24b-instruct-2506","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"mistral-small-3.2-24b-instruct-2506","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.238598816228946e-7,"output_cost_per_token":4.477197632457892e-7},"list_pricing":{"input_cost_per_token":2.238598816228946e-7,"output_cost_per_token":4.477197632457892e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/qwen3-235b-a22b-instruct-2507","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"qwen3-235b-a22b-instruct-2507","context_length":250000,"max_input_tokens":null,"max_output_tokens":16000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0073694673030256e-6,"output_cost_per_token":3.022108401909077e-6},"list_pricing":{"input_cost_per_token":1.0073694673030256e-6,"output_cost_per_token":3.022108401909077e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/qwen3.5-397b-a17b","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"qwen3.5-397b-a17b","context_length":250000,"max_input_tokens":null,"max_output_tokens":16000,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.835095856801311e-7,"output_cost_per_token":4.868952425297957e-6},"list_pricing":{"input_cost_per_token":7.835095856801311e-7,"output_cost_per_token":4.868952425297957e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/qwen3.6-35b-a3b","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"qwen3.6-35b-a3b","context_length":256000,"max_input_tokens":null,"max_output_tokens":32000,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.357898224343419e-7,"output_cost_per_token":2.014738934606051e-6},"list_pricing":{"input_cost_per_token":3.357898224343419e-7,"output_cost_per_token":2.014738934606051e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/green-l","object":"model","created":1791649789,"owned_by":"greenpt","model_name":"green-l","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.798248520286182e-7,"output_cost_per_token":8.954395264915784e-7},"list_pricing":{"input_cost_per_token":2.798248520286182e-7,"output_cost_per_token":8.954395264915784e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/green-l-raw","object":"model","created":1791649789,"owned_by":"greenpt","model_name":"green-l-raw","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.798248520286182e-7,"output_cost_per_token":8.954395264915784e-7},"list_pricing":{"input_cost_per_token":2.798248520286182e-7,"output_cost_per_token":8.954395264915784e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/green-r","object":"model","created":1791649789,"owned_by":"greenpt","model_name":"green-r","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.9175479284006554e-7,"output_cost_per_token":1.0633344377087492e-6},"list_pricing":{"input_cost_per_token":3.9175479284006554e-7,"output_cost_per_token":1.0633344377087492e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/green-r-raw","object":"model","created":1791649789,"owned_by":"greenpt","model_name":"green-r-raw","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.9175479284006554e-7,"output_cost_per_token":1.0633344377087492e-6},"list_pricing":{"input_cost_per_token":3.9175479284006554e-7,"output_cost_per_token":1.0633344377087492e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/glm-5.3","object":"model","created":1791474730,"owned_by":"scaleway","model_name":"glm-5.3","context_length":256000,"max_input_tokens":null,"max_output_tokens":131072,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.014738934606051e-6,"output_cost_per_token":6.156146744629601e-6},"list_pricing":{"input_cost_per_token":2.014738934606051e-6,"output_cost_per_token":6.156146744629601e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4.1-nano","object":"model","created":1791407575,"owned_by":"azure","model_name":"gpt-4.1-nano","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":2.75e-8},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":2.75e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-haiku-5-5","object":"model","created":1791397883,"owned_by":"amazon","model_name":"anthropic.claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-haiku-5-5","object":"model","created":1791397883,"owned_by":"vertex","model_name":"claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-6-1-sol","object":"model","created":1791350016,"owned_by":"databricks","model_name":"databricks-gpt-6-1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-6.1 Sol is OpenAI's upgrade to GPT-6 Sol, with strong performance on agentic coding, computer use, and professional work. It supports text and image inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.00000003e-6,"output_cost_per_token":0.00001000000001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2.00000003e-7,"cache_creation_input_token_cost":2.49998e-6,"input_cost_per_token_above_272k_tokens":4.00001e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens":1.9999e-7,"input_cost_per_token_above_272k_tokens_priority":8.00002e-6,"output_cost_per_token_above_272k_tokens_priority":0.0000299999,"cache_creation_input_token_cost_above_272k_tokens":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens_priority":3.9998e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":9.99999e-6},"list_pricing":{"input_cost_per_token":2.00000003e-6,"output_cost_per_token":0.00001000000001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2.00000003e-7,"cache_creation_input_token_cost":2.49998e-6,"input_cost_per_token_above_272k_tokens":4.00001e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens":1.9999e-7,"input_cost_per_token_above_272k_tokens_priority":8.00002e-6,"output_cost_per_token_above_272k_tokens_priority":0.0000299999,"cache_creation_input_token_cost_above_272k_tokens":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens_priority":3.9998e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":9.99999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-nano-banana-2.1","object":"model","created":1791318261,"owned_by":"vertex","model_name":"gemini-nano-banana-2.1","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.","source":"https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_image":0.00168,"input_cost_per_token":1.5e-6,"output_cost_per_image":0.0336,"output_cost_per_token":7.5e-6,"output_cost_per_image_token":0.00003},"list_pricing":{"input_cost_per_image":0.00168,"input_cost_per_token":1.5e-6,"output_cost_per_image":0.0336,"output_cost_per_token":7.5e-6,"output_cost_per_image_token":0.00003},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-large-4-0","object":"model","created":1791294122,"owned_by":"mistral","model_name":"mistral-large-4-0","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":262144,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.7e-7,"output_cost_per_token":2.31e-6,"cache_read_input_token_cost":7.700000000000001e-8,"input_cost_per_token_batches":3.85e-7,"output_cost_per_token_batches":1.155e-6,"cache_read_input_token_cost_batches":3.850000000000001e-8},"list_pricing":{"input_cost_per_token":7.7e-7,"output_cost_per_token":2.31e-6,"cache_read_input_token_cost":7.700000000000001e-8,"input_cost_per_token_batches":3.85e-7,"output_cost_per_token_batches":1.155e-6,"cache_read_input_token_cost_batches":3.850000000000001e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-large-4","object":"model","created":1791244800,"owned_by":"mistral","model_name":"mistral-large-4","context_length":524288,"max_input_tokens":524288,"max_output_tokens":209715,"description":"Mistral Large 4 (public preview): 1.05T-parameter open-weight multimodal MoE, 49B active.","source":"https://docs.mistral.ai/models/mistral-large-4-0","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7.48e-7,"output_cost_per_token":2.299e-6,"cache_read_input_token_cost":7.700000000000001e-8},"list_pricing":{"input_cost_per_token":7.48e-7,"output_cost_per_token":2.299e-6,"cache_read_input_token_cost":7.700000000000001e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/deepseek-v4.1-flash","object":"model","created":1791211484,"owned_by":"scaleway","model_name":"deepseek-v4.1-flash","context_length":256000,"max_input_tokens":null,"max_output_tokens":32768,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.689999899650001e-7,"output_cost_per_token":2.0069999698950002e-6,"cache_read_input_token_cost":1.3379999799300003e-7},"list_pricing":{"input_cost_per_token":6.689999899650001e-7,"output_cost_per_token":2.0069999698950002e-6,"cache_read_input_token_cost":1.3379999799300003e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/deepseek-v4.1-flash-1017","object":"model","created":1791211484,"owned_by":"scaleway","model_name":"deepseek-v4.1-flash-1017","context_length":256000,"max_input_tokens":null,"max_output_tokens":32768,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.715796448686838e-7,"output_cost_per_token":2.014738934606051e-6,"cache_read_input_token_cost":1.3431592897373677e-7},"list_pricing":{"input_cost_per_token":6.715796448686838e-7,"output_cost_per_token":2.014738934606051e-6,"cache_read_input_token_cost":1.3431592897373677e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenference/gpt-oss-20b","object":"model","created":1791004468,"owned_by":"greenference","model_name":"gpt-oss-20b","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-9,"output_cost_per_token":4.5e-8,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.5e-9,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":9e-9,"output_cost_per_token":4.5e-8,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.5e-9,"cache_creation_input_token_cost":0.0},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"greenference/gemma-4-31b-it","object":"model","created":1790948154,"owned_by":"greenference","model_name":"gemma-4-31b-it","context_length":262144,"max_input_tokens":null,"max_output_tokens":262141,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.485e-7,"output_cost_per_token":4.2e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":5.775e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.485e-7,"output_cost_per_token":4.2e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":5.775e-8,"cache_creation_input_token_cost":0.0},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"greenference/glm-4.7-flash","object":"model","created":1790948154,"owned_by":"greenference","model_name":"glm-4.7-flash","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4.0756e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":1.4331e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4.0756e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":1.4331e-8,"cache_creation_input_token_cost":0.0},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"greenference/glm-5.3-flash","object":"model","created":1790948154,"owned_by":"greenference","model_name":"glm-5.3-flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":0.0},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"greenference/qwen3-14b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3-14b","context_length":41000,"max_input_tokens":null,"max_output_tokens":32768,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.6e-8,"output_cost_per_token":2.28e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":3.8e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":7.6e-8,"output_cost_per_token":2.28e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":3.8e-8,"cache_creation_input_token_cost":0.0},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"greenference/qwen3-30b-a3b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3-30b-a3b","context_length":41000,"max_input_tokens":null,"max_output_tokens":32768,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.5e-8,"output_cost_per_token":2.85e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.75e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":9.5e-8,"output_cost_per_token":2.85e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.75e-8,"cache_creation_input_token_cost":0.0},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"greenference/qwen3-32b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3-32b","context_length":41000,"max_input_tokens":null,"max_output_tokens":32768,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.5e-8,"output_cost_per_token":2.85e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.75e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":9.5e-8,"output_cost_per_token":2.85e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.75e-8,"cache_creation_input_token_cost":0.0},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"greenference/qwen3.5-9b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3.5-9b","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":6.5e-8,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":6.5e-8,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":0.0},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"greenference/qwen3.6-27b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3.6-27b","context_length":262144,"max_input_tokens":null,"max_output_tokens":65536,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.35e-6,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.35e-6,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":0.0},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"greenference/qwen3-8b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3-8b","context_length":41000,"max_input_tokens":null,"max_output_tokens":32768,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":2.5e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":2.5e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":0.0},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"databricks/databricks-claude-sonnet-5-5","object":"model","created":1790917997,"owned_by":"databricks","model_name":"databricks-claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Sonnet 5.5 is Anthropic's model for building features, fixing bugs, and creating documents. It supports a 1 million token context window and up to 128,000 output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.9999999999e-6,"output_cost_per_token":0.000010000000003,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":1.9999999999e-7,"cache_creation_input_token_cost":2.49998e-6,"cache_creation_input_token_cost_above_1hr":4.00001e-6},"list_pricing":{"input_cost_per_token":1.9999999999e-6,"output_cost_per_token":0.000010000000003,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":1.9999999999e-7,"cache_creation_input_token_cost":2.49998e-6,"cache_creation_input_token_cost_above_1hr":4.00001e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6.1-sol","object":"model","created":1790725775,"owned_by":"azure","model_name":"gpt-6.1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1.2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":1.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3e-6,"cache_read_input_token_cost_flex":6e-8,"cache_creation_input_token_cost_flex":1.5e-6,"input_cost_per_token_above_272k_tokens":4.8e-6,"output_cost_per_token_above_272k_tokens":0.000018,"input_cost_per_token_above_272k_tokens_flex":2.4e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":2.4e-7,"cache_creation_input_token_cost_above_272k_tokens":6e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":3e-6},"list_pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1.2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":1.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3e-6,"cache_read_input_token_cost_flex":6e-8,"cache_creation_input_token_cost_flex":1.5e-6,"input_cost_per_token_above_272k_tokens":4.8e-6,"output_cost_per_token_above_272k_tokens":0.000018,"input_cost_per_token_above_272k_tokens_flex":2.4e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":2.4e-7,"cache_creation_input_token_cost_above_272k_tokens":6e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":3e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-5-5","object":"model","created":1790618686,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-5-5","object":"model","created":1790618686,"owned_by":"vertex","model_name":"claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-claude-opus-5-5","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Opus 5.5 is Anthropic's most intelligent model for complex reasoning, coding, and agentic workflows. It uses adaptive thinking to dynamically allocate reasoning effort and supports large-context tasks such as deep document analysis and multi-step tool use. This model is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.9999999998e-6,"output_cost_per_token":0.000019999999999,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":3.9999999998e-7,"cache_creation_input_token_cost":5.00003e-6,"cache_creation_input_token_cost_above_1hr":8.00002e-6},"list_pricing":{"input_cost_per_token":3.9999999998e-6,"output_cost_per_token":0.000019999999999,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":3.9999999998e-7,"cache_creation_input_token_cost":5.00003e-6,"cache_creation_input_token_cost_above_1hr":8.00002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-6-luna","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 family, bringing strong reasoning and agentic capability at the lowest cost in the lineup. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000003e-7,"output_cost_per_token":5.0000000001e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.0000000003e-8,"cache_creation_input_token_cost":1.2502e-7,"input_cost_per_token_above_272k_tokens":1.9999e-7,"output_cost_per_token_above_272k_tokens":7.497e-7,"cache_creation_input_token_cost_priority":2.4997e-7,"cache_read_input_token_cost_above_272k_tokens":2.002e-8,"input_cost_per_token_above_272k_tokens_priority":3.9998e-7,"output_cost_per_token_above_272k_tokens_priority":1.5001e-6,"cache_creation_input_token_cost_above_272k_tokens":2.4997e-7,"cache_read_input_token_cost_above_272k_tokens_priority":3.997e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5.0001e-7},"list_pricing":{"input_cost_per_token":1.0000000003e-7,"output_cost_per_token":5.0000000001e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.0000000003e-8,"cache_creation_input_token_cost":1.2502e-7,"input_cost_per_token_above_272k_tokens":1.9999e-7,"output_cost_per_token_above_272k_tokens":7.497e-7,"cache_creation_input_token_cost_priority":2.4997e-7,"cache_read_input_token_cost_above_272k_tokens":2.002e-8,"input_cost_per_token_above_272k_tokens_priority":3.9998e-7,"output_cost_per_token_above_272k_tokens_priority":1.5001e-6,"cache_creation_input_token_cost_above_272k_tokens":2.4997e-7,"cache_read_input_token_cost_above_272k_tokens_priority":3.997e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5.0001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-6-sol","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-gpt-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-6 Sol is OpenAI's flagship model in the GPT-6 family, delivering state-of-the-art performance on agentic coding, long-horizon reasoning, and complex tool use. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.9999999999e-6,"output_cost_per_token":0.000010000000003,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":1.9999999999e-7,"cache_creation_input_token_cost":2.49998e-6,"input_cost_per_token_above_272k_tokens":4.00001e-6,"output_cost_per_token_above_272k_tokens":0.0000150003,"cache_creation_input_token_cost_priority":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens":3.9998e-7,"input_cost_per_token_above_272k_tokens_priority":8.00002e-6,"output_cost_per_token_above_272k_tokens_priority":0.0000299999,"cache_creation_input_token_cost_above_272k_tokens":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.0003e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":9.99999e-6},"list_pricing":{"input_cost_per_token":1.9999999999e-6,"output_cost_per_token":0.000010000000003,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":1.9999999999e-7,"cache_creation_input_token_cost":2.49998e-6,"input_cost_per_token_above_272k_tokens":4.00001e-6,"output_cost_per_token_above_272k_tokens":0.0000150003,"cache_creation_input_token_cost_priority":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens":3.9998e-7,"input_cost_per_token_above_272k_tokens_priority":8.00002e-6,"output_cost_per_token_above_272k_tokens_priority":0.0000299999,"cache_creation_input_token_cost_above_272k_tokens":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.0003e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":9.99999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6-luna","object":"model","created":1790188180,"owned_by":"azure","model_name":"gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":6e-8,"output_cost_per_token_flex":3e-7,"cache_read_input_token_cost":1.2e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.5e-7,"cache_read_input_token_cost_flex":6e-9,"cache_creation_input_token_cost_flex":7.5e-8,"input_cost_per_token_above_272k_tokens":2.4e-7,"output_cost_per_token_above_272k_tokens":9e-7,"input_cost_per_token_above_272k_tokens_flex":1.2e-7,"output_cost_per_token_above_272k_tokens_flex":4.5e-7,"cache_read_input_token_cost_above_272k_tokens":2.4e-8,"cache_creation_input_token_cost_above_272k_tokens":3e-7,"cache_read_input_token_cost_above_272k_tokens_flex":1.2e-8,"cache_creation_input_token_cost_above_272k_tokens_flex":1.5e-7},"list_pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":6e-8,"output_cost_per_token_flex":3e-7,"cache_read_input_token_cost":1.2e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.5e-7,"cache_read_input_token_cost_flex":6e-9,"cache_creation_input_token_cost_flex":7.5e-8,"input_cost_per_token_above_272k_tokens":2.4e-7,"output_cost_per_token_above_272k_tokens":9e-7,"input_cost_per_token_above_272k_tokens_flex":1.2e-7,"output_cost_per_token_above_272k_tokens_flex":4.5e-7,"cache_read_input_token_cost_above_272k_tokens":2.4e-8,"cache_creation_input_token_cost_above_272k_tokens":3e-7,"cache_read_input_token_cost_above_272k_tokens_flex":1.2e-8,"cache_creation_input_token_cost_above_272k_tokens_flex":1.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6-sol","object":"model","created":1790188180,"owned_by":"azure","model_name":"gpt-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1.2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2.4e-7,"input_cost_per_token_priority":4.8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":3e-6,"cache_read_input_token_cost_flex":1.2e-7,"cache_creation_input_token_cost_flex":1.5e-6,"cache_read_input_token_cost_priority":4.8e-7,"input_cost_per_token_above_272k_tokens":4.8e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":6e-6,"input_cost_per_token_above_272k_tokens_flex":2.4e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":4.8e-7,"input_cost_per_token_above_272k_tokens_priority":9.6e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":6e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":3e-6,"cache_read_input_token_cost_above_272k_tokens_priority":9.6e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000012},"list_pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1.2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2.4e-7,"input_cost_per_token_priority":4.8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":3e-6,"cache_read_input_token_cost_flex":1.2e-7,"cache_creation_input_token_cost_flex":1.5e-6,"cache_read_input_token_cost_priority":4.8e-7,"input_cost_per_token_above_272k_tokens":4.8e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":6e-6,"input_cost_per_token_above_272k_tokens_flex":2.4e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":4.8e-7,"input_cost_per_token_above_272k_tokens_priority":9.6e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":6e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":3e-6,"cache_read_input_token_cost_above_272k_tokens_priority":9.6e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000012},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gemini-3-7-flash","object":"model","created":1790140226,"owned_by":"databricks","model_name":"databricks-gemini-3-7-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.7 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.4999995e-7,"output_cost_per_token":3.74999975e-6,"cache_read_input_token_cost":7.4999995e-8,"cache_creation_input_token_cost":7.4998e-7,"cache_creation_input_token_cost_priority":1.35002e-6},"list_pricing":{"input_cost_per_token":7.4999995e-7,"output_cost_per_token":3.74999975e-6,"cache_read_input_token_cost":7.4999995e-8,"cache_creation_input_token_cost":7.4998e-7,"cache_creation_input_token_cost_priority":1.35002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gemini-3-8-flash","object":"model","created":1790140226,"owned_by":"databricks","model_name":"databricks-gemini-3-8-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.8 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.4999995e-7,"output_cost_per_token":3.74999975e-6,"cache_read_input_token_cost":7.4999995e-8,"cache_creation_input_token_cost":7.4998e-7,"cache_creation_input_token_cost_priority":1.35002e-6},"list_pricing":{"input_cost_per_token":7.4999995e-7,"output_cost_per_token":3.74999975e-6,"cache_read_input_token_cost":7.4999995e-8,"cache_creation_input_token_cost":7.4998e-7,"cache_creation_input_token_cost_priority":1.35002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-opus-5-5","object":"model","created":1790094732,"owned_by":"amazon","model_name":"anthropic.claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-5-5","object":"model","created":1790094732,"owned_by":"vertex","model_name":"claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-6-astra","object":"model","created":1789744452,"owned_by":"databricks","model_name":"databricks-gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-6 Astra is OpenAI's frontier model for enterprise reasoning and structured document processing. It excels at complex document reasoning and parsing, while offering capable coding and agentic search performance. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.9999998e-6,"output_cost_per_token":0.0000499999997,"input_dbu_cost_per_token":0.00014286,"output_dbu_cost_per_token":0.00071429,"cache_read_input_token_cost":9.9999998e-7,"cache_creation_input_token_cost":0.00001249997,"input_cost_per_token_above_32k_tokens":0.00001999998,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_32k_tokens":0.0000750001,"output_cost_per_token_above_272k_tokens":0.0000750001,"cache_creation_input_token_cost_priority":0.00002500001,"cache_read_input_token_cost_above_32k_tokens":1.99997e-6,"cache_read_input_token_cost_above_272k_tokens":1.99997e-6,"input_cost_per_token_above_272k_tokens_priority":0.00004000003,"cache_creation_input_token_cost_above_32k_tokens":0.00002500001,"output_cost_per_token_above_272k_tokens_priority":0.0001500002,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_priority":4.00001e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005000002},"list_pricing":{"input_cost_per_token":9.9999998e-6,"output_cost_per_token":0.0000499999997,"input_dbu_cost_per_token":0.00014286,"output_dbu_cost_per_token":0.00071429,"cache_read_input_token_cost":9.9999998e-7,"cache_creation_input_token_cost":0.00001249997,"input_cost_per_token_above_32k_tokens":0.00001999998,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_32k_tokens":0.0000750001,"output_cost_per_token_above_272k_tokens":0.0000750001,"cache_creation_input_token_cost_priority":0.00002500001,"cache_read_input_token_cost_above_32k_tokens":1.99997e-6,"cache_read_input_token_cost_above_272k_tokens":1.99997e-6,"input_cost_per_token_above_272k_tokens_priority":0.00004000003,"cache_creation_input_token_cost_above_32k_tokens":0.00002500001,"output_cost_per_token_above_272k_tokens_priority":0.0001500002,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_priority":4.00001e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005000002},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"ovhcloud/Qwen3.8-27B","object":"model","created":1789657955,"owned_by":"ovhcloud","model_name":"Qwen3.8-27B","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.7e-7,"output_cost_per_token":3.19e-6},"list_pricing":{"input_cost_per_token":4.7e-7,"output_cost_per_token":3.19e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/zai-glm-5","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-5","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"list_pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/zai-glm-5-3","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-5-3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"list_pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/zai-glm-latest","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-latest","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"list_pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/qwen3.8-27b","object":"model","created":1789565546,"owned_by":"scaleway","model_name":"qwen3.8-27b","context_length":256000,"max_input_tokens":null,"max_output_tokens":131072,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.715796448686838e-7,"output_cost_per_token":3.693688046777761e-6,"cache_read_input_token_cost":1.3431592897373677e-7},"list_pricing":{"input_cost_per_token":6.715796448686838e-7,"output_cost_per_token":3.693688046777761e-6,"cache_read_input_token_cost":1.3431592897373677e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4.1-flash","object":"model","created":1789362586,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4.1-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.25e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/deepseek.v3-v1:0","object":"model","created":1789016966,"owned_by":"amazon","model_name":"deepseek.v3-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.8e-7,"output_cost_per_token":1.68e-6},"list_pricing":{"input_cost_per_token":5.8e-7,"output_cost_per_token":1.68e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/qwen.qwen3-235b-a22b-2507-v1:0","object":"model","created":1789016966,"owned_by":"amazon","model_name":"qwen.qwen3-235b-a22b-2507-v1:0","context_length":262144,"max_input_tokens":262144,"max_output_tokens":8192,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":8.8e-7,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":4.4e-7},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":8.8e-7,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":4.4e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/qwen.qwen3-coder-480b-a35b-v1:0","object":"model","created":1789016966,"owned_by":"amazon","model_name":"qwen.qwen3-coder-480b-a35b-v1:0","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5e-7,"output_cost_per_token":1.8e-6},"list_pricing":{"input_cost_per_token":4.5e-7,"output_cost_per_token":1.8e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"compactifai/carina-60b","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"carina-60b","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-8,"output_cost_per_token":8.5e-8},"list_pricing":{"input_cost_per_token":2.2e-8,"output_cost_per_token":8.5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"compactifai/qwen-3-8-27b","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"qwen-3-8-27b","context_length":null,"max_input_tokens":null,"max_output_tokens":131072,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.71e-8},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.71e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"vertex/gemini-3.8-flash","object":"model","created":1788362056,"owned_by":"vertex","model_name":"gemini-3.8-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"cache_read_input_token_cost":7.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_audio_token_cost":7.5e-8,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":8.33333333333334e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_audio_token_cost":1.5e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-fable-5-1","object":"model","created":1788285838,"owned_by":"vertex","model_name":"claude-fable-5-1","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":2.75e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"list_pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":2.75e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"ionos/Qwen/Qwen3.8-27B","object":"model","created":1788215842,"owned_by":"ionos","model_name":"Qwen/Qwen3.8-27B","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.477197632457892e-7,"output_cost_per_token":3.022108401909077e-6},"list_pricing":{"input_cost_per_token":4.477197632457892e-7,"output_cost_per_token":3.022108401909077e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-code-agent-latest","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-code-agent-latest","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-code-fim-latest","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-code-fim-latest","context_length":256000,"max_input_tokens":128000,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-code-latest","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-code-latest","context_length":256000,"max_input_tokens":128000,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-vibe-cli-fast","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-vibe-cli-fast","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-vibe-cli-latest","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-vibe-cli-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-vibe-cli-with-tools","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-vibe-cli-with-tools","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4-pro-0813","object":"model","created":1787980172,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4-pro-0813","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":5e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5.3","object":"model","created":1787980172,"owned_by":"tensorx","model_name":"z-ai/glm-5.3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":4.375e-7},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":4.375e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/qwen/qwen3.8-flash-next","object":"model","created":1787929919,"owned_by":"tensorx","model_name":"qwen/qwen3.8-flash-next","context_length":262144,"max_input_tokens":262144,"max_output_tokens":64000,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5.3-flash","object":"model","created":1787929919,"owned_by":"tensorx","model_name":"z-ai/glm-5.3-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/ministral-14b-latest","object":"model","created":1787893793,"owned_by":"mistral","model_name":"ministral-14b-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-7,"cache_read_input_token_cost":2.2000000000000002e-8,"input_cost_per_token_batches":1.1e-7,"output_cost_per_token_batches":1.1e-7,"cache_read_input_token_cost_batches":1.1000000000000001e-8},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-7,"cache_read_input_token_cost":2.2000000000000002e-8,"input_cost_per_token_batches":1.1e-7,"output_cost_per_token_batches":1.1e-7,"cache_read_input_token_cost_batches":1.1000000000000001e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/ministral-3b-latest","object":"model","created":1787893793,"owned_by":"mistral","model_name":"ministral-3b-latest","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":1.1e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":1.1e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/voxtral-small-2507","object":"model","created":1787893793,"owned_by":"mistral","model_name":"voxtral-small-2507","context_length":32768,"max_input_tokens":32768,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":2.2e-7,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":2.2e-7,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/voxtral-small-latest","object":"model","created":1787893793,"owned_by":"mistral","model_name":"voxtral-small-latest","context_length":32768,"max_input_tokens":32768,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":2.2e-7,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":2.2e-7,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/zai-glm-5-2","object":"model","created":1787288981,"owned_by":"mistral","model_name":"zai-glm-5-2","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7},"list_pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"tensorx/deepseek/deepseek-r1-0528","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"deepseek/deepseek-r1-0528","context_length":164000,"max_input_tokens":164000,"max_output_tokens":8192,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":2.6e-6,"cache_read_input_token_cost":1.65e-7},"list_pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":2.6e-6,"cache_read_input_token_cost":1.65e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v3.2","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"deepseek/deepseek-v3.2","context_length":163840,"max_input_tokens":163840,"max_output_tokens":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":7.5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4-flash-0731","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4-flash-0731","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":"Served by TensorX at fp4 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":6.25e-8},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":6.25e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4-pro","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":4.375e-7},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":4.375e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/minimax/minimax-m2.5","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"minimax/minimax-m2.5","context_length":196608,"max_input_tokens":196608,"max_output_tokens":65536,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/minimax/minimax-m3","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"minimax/minimax-m3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/moonshotai/kimi-k2.5","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"moonshotai/kimi-k2.5","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":"Served by TensorX at int4 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.8e-6,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.8e-6,"cache_read_input_token_cost":1.25e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/moonshotai/kimi-k2.6","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"moonshotai/kimi-k2.6","context_length":262144,"max_input_tokens":262144,"max_output_tokens":64000,"description":"Served by TensorX at int4 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.5e-7},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/moonshotai/kimi-k2.7-code","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"moonshotai/kimi-k2.7-code","context_length":262144,"max_input_tokens":262144,"max_output_tokens":64000,"description":"Served by TensorX at int4 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":3.125e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":3.125e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/moonshotai/kimi-k3","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"moonshotai/kimi-k3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":"Served by TensorX at mxfp4 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/qwen/qwen3-235b-a22b-2507","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"qwen/qwen3-235b-a22b-2507","context_length":131000,"max_input_tokens":131000,"max_output_tokens":32768,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.2e-8,"output_cost_per_token":4.64e-7,"cache_read_input_token_cost":1.8e-8},"list_pricing":{"input_cost_per_token":7.2e-8,"output_cost_per_token":4.64e-7,"cache_read_input_token_cost":1.8e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/qwen/qwen3.5-122b-a10b","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"qwen/qwen3.5-122b-a10b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":1.25e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/qwen/qwen3.5-9b","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"qwen/qwen3.5-9b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":3.75e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":3.75e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/qwen/qwen3.8-2.4t-a95b","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"qwen/qwen3.8-2.4t-a95b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":64000,"description":"Served by TensorX at nvfp4 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":6.25e-7},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":6.25e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/qwen/qwen3.8-27b","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"qwen/qwen3.8-27b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131072,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"cache_read_input_token_cost":2.5e-7},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"cache_read_input_token_cost":2.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5.1","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5.1","context_length":202752,"max_input_tokens":202752,"max_output_tokens":64000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":3.5e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":3.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5.2","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5.2","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":3.75e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":3.75e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5-turbo","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5-turbo","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131072,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":3e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5v-turbo","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5v-turbo","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131072,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":3e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/DeepSeek-V4-Flash-0731","object":"model","created":1786684194,"owned_by":"flexai","model_name":"DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.19e-7,"output_cost_per_token":2.38e-7,"cache_read_input_token_cost":1.78e-8},"list_pricing":{"input_cost_per_token":1.19e-7,"output_cost_per_token":2.38e-7,"cache_read_input_token_cost":1.78e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/meta-llama/Llama-3.3-70B-Instruct","object":"model","created":1786647205,"owned_by":"ionos","model_name":"meta-llama/Llama-3.3-70B-Instruct","context_length":128000,"max_input_tokens":null,"max_output_tokens":null,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.275446152744074e-7,"output_cost_per_token":7.275446152744074e-7},"list_pricing":{"input_cost_per_token":7.275446152744074e-7,"output_cost_per_token":7.275446152744074e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/mistralai/Mistral-Small-24B-Instruct","object":"model","created":1786647205,"owned_by":"ionos","model_name":"mistralai/Mistral-Small-24B-Instruct","context_length":128000,"max_input_tokens":null,"max_output_tokens":32768,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.119299408114473e-7,"output_cost_per_token":3.357898224343419e-7},"list_pricing":{"input_cost_per_token":1.119299408114473e-7,"output_cost_per_token":3.357898224343419e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/openai/gpt-oss-120b","object":"model","created":1786647205,"owned_by":"ionos","model_name":"openai/gpt-oss-120b","context_length":128000,"max_input_tokens":null,"max_output_tokens":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6789491121717094e-7,"output_cost_per_token":7.275446152744074e-7},"list_pricing":{"input_cost_per_token":1.6789491121717094e-7,"output_cost_per_token":7.275446152744074e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/Qwen/Qwen3.5-397B-A17B","object":"model","created":1786647205,"owned_by":"ionos","model_name":"Qwen/Qwen3.5-397B-A17B","context_length":262144,"max_input_tokens":null,"max_output_tokens":65536,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.715796448686838e-7,"output_cost_per_token":4.029477869212102e-6},"list_pricing":{"input_cost_per_token":6.715796448686838e-7,"output_cost_per_token":4.029477869212102e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/Qwen/Qwen3.5-9B","object":"model","created":1786647205,"owned_by":"ionos","model_name":"Qwen/Qwen3.5-9B","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.119299408114473e-7,"output_cost_per_token":1.6789491121717094e-7},"list_pricing":{"input_cost_per_token":1.119299408114473e-7,"output_cost_per_token":1.6789491121717094e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/Qwen/Qwen3-Coder-Next","object":"model","created":1786647205,"owned_by":"ionos","model_name":"Qwen/Qwen3-Coder-Next","context_length":128000,"max_input_tokens":null,"max_output_tokens":null,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6789491121717094e-7,"output_cost_per_token":8.954395264915784e-7},"list_pricing":{"input_cost_per_token":1.6789491121717094e-7,"output_cost_per_token":8.954395264915784e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.7-flash","object":"model","created":1786640581,"owned_by":"vertex","model_name":"gemini-3.7-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"cache_read_input_token_cost":7.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_audio_token_cost":7.5e-8,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":8.33333333333334e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_audio_token_cost":1.5e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/deepseek-v4-flash","object":"model","created":1786613111,"owned_by":"azure","model_name":"deepseek-v4-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0900000000000003e-7,"output_cost_per_token":5.61e-7,"cache_read_input_token_cost":3.0800000000000004e-8},"list_pricing":{"input_cost_per_token":2.0900000000000003e-7,"output_cost_per_token":5.61e-7,"cache_read_input_token_cost":3.0800000000000004e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4.1","object":"model","created":1786613111,"owned_by":"azure","model_name":"gpt-4.1","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_priority":3.85e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000154,"cache_read_input_token_cost_priority":9.625e-7},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_priority":3.85e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000154,"cache_read_input_token_cost_priority":9.625e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4.1-mini","object":"model","created":1786613111,"owned_by":"azure","model_name":"gpt-4.1-mini","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":1.76e-6,"cache_read_input_token_cost":1.1e-7,"input_cost_per_token_priority":7.7e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.08e-6,"cache_read_input_token_cost_priority":1.925e-7},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":1.76e-6,"cache_read_input_token_cost":1.1e-7,"input_cost_per_token_priority":7.7e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.08e-6,"cache_read_input_token_cost_priority":1.925e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/mistral-large-3","object":"model","created":1786613111,"owned_by":"azure","model_name":"mistral-large-3","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8191,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.5e-7,"output_cost_per_token":1.65e-6},"list_pricing":{"input_cost_per_token":5.5e-7,"output_cost_per_token":1.65e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/gemma-4-26B-A4B-it","object":"model","created":1786610410,"owned_by":"flexai","model_name":"gemma-4-26B-A4B-it","context_length":262144,"max_input_tokens":null,"max_output_tokens":32768,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":1.05e-8},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":1.05e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/gemma-4-31b-it","object":"model","created":1786610410,"owned_by":"flexai","model_name":"gemma-4-31b-it","context_length":262144,"max_input_tokens":null,"max_output_tokens":32768,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":2.1e-8},"list_pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":2.1e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/deepseek-v4-flash-0731","object":"model","created":1786376637,"owned_by":"scaleway","model_name":"deepseek-v4-flash-0731","context_length":256000,"max_input_tokens":null,"max_output_tokens":32768,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.477197632457892e-7,"output_cost_per_token":8.954395264915784e-7,"cache_read_input_token_cost":8.954395264915784e-8},"list_pricing":{"input_cost_per_token":4.477197632457892e-7,"output_cost_per_token":8.954395264915784e-7,"cache_read_input_token_cost":8.954395264915784e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-claude-opus-5","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Opus 5 is Anthropic's latest Opus-class model, delivering frontier intelligence for complex reasoning, coding, and agentic workflows at Opus-tier pricing. It features an adjustable effort control to trade off thoroughness against latency and cost, and supports large-context tasks such as deep document analysis and multi-step tool use. This model is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4.99999997e-6,"output_cost_per_token":0.00002499999999,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":4.99999997e-7,"cache_creation_input_token_cost":6.25002e-6,"cache_creation_input_token_cost_above_1hr":9.99999e-6},"list_pricing":{"input_cost_per_token":4.99999997e-6,"output_cost_per_token":0.00002499999999,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":4.99999997e-7,"cache_creation_input_token_cost":6.25002e-6,"cache_creation_input_token_cost_above_1hr":9.99999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-sonnet-5","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Sonnet 5 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.999998e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":1.999998e-7,"cache_creation_input_token_cost":2.49998e-6,"cache_creation_input_token_cost_above_1hr":4.00001e-6},"list_pricing":{"input_cost_per_token":1.999998e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":1.999998e-7,"cache_creation_input_token_cost":2.49998e-6,"cache_creation_input_token_cost_above_1hr":4.00001e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gemini-3-1-flash-lite","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gemini-3-1-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.1 Flash Lite is Google's fastest and most cost-efficient model in the Gemini 3 series, designed for high-volume and latency-sensitive workloads at scale. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.4997e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":4.464e-6,"output_dbu_cost_per_token":0.000026786,"input_cost_per_audio_token":6.2503e-7,"input_cost_per_image_token":3.1248e-7,"cache_read_input_token_cost":2.4997e-8,"cache_creation_input_token_cost":3.1248e-7,"cache_read_input_audio_token_cost":6.251e-8,"input_cost_per_audio_token_priority":1.12497e-6,"cache_creation_input_token_cost_priority":5.6252e-7,"cache_read_input_audio_token_cost_priority":1.1249e-7},"list_pricing":{"input_cost_per_token":2.4997e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":4.464e-6,"output_dbu_cost_per_token":0.000026786,"input_cost_per_audio_token":6.2503e-7,"input_cost_per_image_token":3.1248e-7,"cache_read_input_token_cost":2.4997e-8,"cache_creation_input_token_cost":3.1248e-7,"cache_read_input_audio_token_cost":6.251e-8,"input_cost_per_audio_token_priority":1.12497e-6,"cache_creation_input_token_cost_priority":5.6252e-7,"cache_read_input_audio_token_cost_priority":1.1249e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gemini-3-5-flash","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gemini-3-5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.5 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.499995e-6,"output_cost_per_token":8.99997e-6,"input_dbu_cost_per_token":0.000026786,"output_dbu_cost_per_token":0.000160714,"cache_read_input_token_cost":1.499995e-7,"cache_creation_input_token_cost":1.87502e-6,"cache_creation_input_token_cost_priority":3.37498e-6},"list_pricing":{"input_cost_per_token":1.499995e-6,"output_cost_per_token":8.99997e-6,"input_dbu_cost_per_token":0.000026786,"output_dbu_cost_per_token":0.000160714,"cache_read_input_token_cost":1.499995e-7,"cache_creation_input_token_cost":1.87502e-6,"cache_creation_input_token_cost_priority":3.37498e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-2","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gpt-5-2","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5.2 is a general purpose large language model with reasoning capabilities developed by OpenAI. This model builds directly upon GPT-5.1, offering higher accuracy, improved token efficiency on medium-to-complex tasks, and more deliberate scaffolded reasoning. This model excels at structured extraction, multi-step workflows, and multimodal tasks. It supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_dbu_cost_per_token":0.000025,"output_dbu_cost_per_token":0.0002,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.000028,"cache_creation_input_token_cost":1.75e-6,"cache_read_input_token_cost_priority":3.5e-7,"cache_creation_input_token_cost_priority":3.5e-6},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_dbu_cost_per_token":0.000025,"output_dbu_cost_per_token":0.0002,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.000028,"cache_creation_input_token_cost":1.75e-6,"cache_read_input_token_cost_priority":3.5e-7,"cache_creation_input_token_cost_priority":3.5e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-5-pro","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gpt-5-5-pro","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-5.5 Pro is OpenAI's strongest frontier model for agentic work in enterprise, complex document reasoning, and long-horizon coding agents. GPT-5.5 Pro also now powers Codex, OpenAI's coding agent. Pro uses more compute to think harder and provide consistently better answers. This model supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":0.00002999997,"output_cost_per_token":0.0001799994,"input_dbu_cost_per_token":0.00042857,"output_dbu_cost_per_token":0.0025714,"cache_read_input_token_cost":2.999997e-6,"cache_creation_input_token_cost":0.00002999997,"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"list_pricing":{"input_cost_per_token":0.00002999997,"output_cost_per_token":0.0001799994,"input_dbu_cost_per_token":0.00042857,"output_dbu_cost_per_token":0.0025714,"cache_read_input_token_cost":2.999997e-6,"cache_creation_input_token_cost":0.00002999997,"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-qwen35-122b-a10b","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-qwen35-122b-a10b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.199995e-7,"output_cost_per_token":2.199995e-6,"input_dbu_cost_per_token":3.143e-6,"output_dbu_cost_per_token":0.000031429,"cache_read_input_token_cost":2.199995e-8,"cache_creation_input_token_cost":2.2001e-7,"cache_creation_input_token_cost_priority":3.85e-7},"list_pricing":{"input_cost_per_token":2.199995e-7,"output_cost_per_token":2.199995e-6,"input_dbu_cost_per_token":3.143e-6,"output_dbu_cost_per_token":0.000031429,"cache_read_input_token_cost":2.199995e-8,"cache_creation_input_token_cost":2.2001e-7,"cache_creation_input_token_cost_priority":3.85e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-qwen3-next-80b-a3b-instruct","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-qwen3-next-80b-a3b-instruct","context_length":null,"max_input_tokens":null,"max_output_tokens":262144,"description":"Qwen3-Next-80B-A3B-Instruct is a highly efficient large language model optimized for instruction-following tasks built and trained by Alibaba Cloud. This model is designed to handle ultra-long contexts and excels at multi-step workflows, retrieval-augmented generation, and enterprise applications that require deterministic outputs at high throughput. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":1.20001e-6,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"list_pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":1.20001e-6,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"qwen/qwen3.5-flash","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3.5-flash","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_creation_input_token_cost":8.125e-8},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":4.0000000000000003e-7,"cache_creation_input_token_cost":1.25e-7},"discount":0.35,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"qwen/qwen3.5-flash-2026-02-23","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3.5-flash-2026-02-23","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.This version is a snapshot as of February 23, 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":4.0000000000000003e-7},"discount":0.35,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"qwen/qwen3-vl-plus","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3-vl-plus","context_length":262144,"max_input_tokens":258048,"max_output_tokens":32768,"description":"The Qwen3 series VL models effectively integrates thinking and non-thinking modes, achieving world-leading performance in visual agent capabilities on public benchmark datasets such as OS World. This version features comprehensive upgrades in areas like visual coding, spatial perception, and multimodal reasoning, significantly enhancing visual perception and recognition abilities, and supporting the understanding of ultra-long videos.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7},{"range":[32000,128000],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_read_input_token_cost":3.9e-8,"cache_creation_input_token_cost":2.4375e-7},{"range":[128000,256000],"input_cost_per_token":3.8999999999999997e-7,"output_cost_per_token":3.1199999999999998e-6,"cache_read_input_token_cost":7.8e-8,"cache_creation_input_token_cost":4.875e-7}],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":1.6000000000000001e-6,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":2.5e-7},{"range":[32000,128000],"input_cost_per_token":3e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":6e-8,"cache_creation_input_token_cost":3.75e-7},{"range":[128000,256000],"input_cost_per_token":6e-7,"output_cost_per_token":4.8e-6,"cache_read_input_token_cost":1.2e-7,"cache_creation_input_token_cost":7.5e-7}],"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":1.6000000000000001e-6,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":2.5e-7},"discount":0.35,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"azure/gpt-5.5","object":"model","created":1785276709,"owned_by":"azure","model_name":"gpt-5.5","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000033,"input_cost_per_token_flex":2.7500000000000004e-6,"cache_read_input_token_cost":5.500000000000001e-7,"input_cost_per_token_priority":0.000013750000000000002,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000825,"cache_creation_input_token_cost":6.875000000000001e-6,"cache_read_input_token_cost_flex":2.75e-7,"cache_read_input_token_cost_priority":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":0.000011000000000000001,"output_cost_per_token_above_272k_tokens":0.000049500000000000004,"input_cost_per_token_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens":1.1000000000000003e-6,"input_cost_per_token_above_272k_tokens_priority":0.000022000000000000003,"output_cost_per_token_above_272k_tokens_priority":0.00009900000000000001,"cache_creation_input_token_cost_above_272k_tokens":0.000013750000000000002,"cache_read_input_token_cost_above_272k_tokens_priority":2.2e-6},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000033,"input_cost_per_token_flex":2.7500000000000004e-6,"cache_read_input_token_cost":5.500000000000001e-7,"input_cost_per_token_priority":0.000013750000000000002,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000825,"cache_creation_input_token_cost":6.875000000000001e-6,"cache_read_input_token_cost_flex":2.75e-7,"cache_read_input_token_cost_priority":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":0.000011000000000000001,"output_cost_per_token_above_272k_tokens":0.000049500000000000004,"input_cost_per_token_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens":1.1000000000000003e-6,"input_cost_per_token_above_272k_tokens_priority":0.000022000000000000003,"output_cost_per_token_above_272k_tokens_priority":0.00009900000000000001,"cache_creation_input_token_cost_above_272k_tokens":0.000013750000000000002,"cache_read_input_token_cost_above_272k_tokens_priority":2.2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4o","object":"model","created":1784916453,"owned_by":"azure","model_name":"gpt-4o","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.3750000000000002e-6},"list_pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.3750000000000002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4o-mini","object":"model","created":1784916453,"owned_by":"azure","model_name":"gpt-4o-mini","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":8.25e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":8.25e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/o3","object":"model","created":1784916453,"owned_by":"azure","model_name":"o3","context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-5","object":"model","created":1784912544,"owned_by":"amazon","model_name":"anthropic.claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-5","object":"model","created":1784912544,"owned_by":"vertex","model_name":"claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.4","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.0000165,"input_cost_per_token_flex":1.3750000000000002e-6,"output_cost_per_token_flex":8.25e-6,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_priority":5.500000000000001e-6,"output_cost_per_token_priority":0.000033,"cache_read_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens":5.500000000000001e-6,"output_cost_per_token_above_272k_tokens":0.000024750000000000002,"input_cost_per_token_above_272k_tokens_flex":2.7500000000000004e-6,"output_cost_per_token_above_272k_tokens_flex":0.000012375000000000001,"cache_read_input_token_cost_above_272k_tokens":5.5e-7,"input_cost_per_token_above_272k_tokens_priority":0.000011000000000000001,"output_cost_per_token_above_272k_tokens_priority":0.000049500000000000004,"cache_read_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":1.1e-6},"list_pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.0000165,"input_cost_per_token_flex":1.3750000000000002e-6,"output_cost_per_token_flex":8.25e-6,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_priority":5.500000000000001e-6,"output_cost_per_token_priority":0.000033,"cache_read_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens":5.500000000000001e-6,"output_cost_per_token_above_272k_tokens":0.000024750000000000002,"input_cost_per_token_above_272k_tokens_flex":2.7500000000000004e-6,"output_cost_per_token_above_272k_tokens_flex":0.000012375000000000001,"cache_read_input_token_cost_above_272k_tokens":5.5e-7,"input_cost_per_token_above_272k_tokens_priority":0.000011000000000000001,"output_cost_per_token_above_272k_tokens_priority":0.000049500000000000004,"cache_read_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":1.1e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.4-mini","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"input_cost_per_token_flex":4.125e-7,"output_cost_per_token_flex":2.4750000000000004e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9.900000000000002e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_token_cost_priority":1.65e-7},"list_pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"input_cost_per_token_flex":4.125e-7,"output_cost_per_token_flex":2.4750000000000004e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9.900000000000002e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_token_cost_priority":1.65e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.6-luna","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2000000000000004e-7,"output_cost_per_token":1.32e-6,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":6.6e-7,"cache_read_input_token_cost":2.2000000000000005e-8,"input_cost_per_token_priority":4.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.64e-6,"cache_creation_input_token_cost":2.7500000000000007e-7,"cache_read_input_token_cost_flex":1.1000000000000001e-8,"cache_creation_input_token_cost_flex":1.375e-7,"cache_read_input_token_cost_priority":4.4000000000000004e-8,"input_cost_per_token_above_272k_tokens":4.400000000000001e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_creation_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens_flex":2.2e-7,"output_cost_per_token_above_272k_tokens_flex":9.9e-7,"cache_read_input_token_cost_above_272k_tokens":4.400000000000001e-8,"input_cost_per_token_above_272k_tokens_priority":8.8e-7,"output_cost_per_token_above_272k_tokens_priority":3.96e-6,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2.2000000000000002e-8,"cache_creation_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8.800000000000001e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1.1e-6},"list_pricing":{"input_cost_per_token":2.2000000000000004e-7,"output_cost_per_token":1.32e-6,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":6.6e-7,"cache_read_input_token_cost":2.2000000000000005e-8,"input_cost_per_token_priority":4.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.64e-6,"cache_creation_input_token_cost":2.7500000000000007e-7,"cache_read_input_token_cost_flex":1.1000000000000001e-8,"cache_creation_input_token_cost_flex":1.375e-7,"cache_read_input_token_cost_priority":4.4000000000000004e-8,"input_cost_per_token_above_272k_tokens":4.400000000000001e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_creation_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens_flex":2.2e-7,"output_cost_per_token_above_272k_tokens_flex":9.9e-7,"cache_read_input_token_cost_above_272k_tokens":4.400000000000001e-8,"input_cost_per_token_above_272k_tokens_priority":8.8e-7,"output_cost_per_token_above_272k_tokens_priority":3.96e-6,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2.2000000000000002e-8,"cache_creation_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8.800000000000001e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1.1e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.6-sol","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_token_flex":2.2e-6,"output_cost_per_token_flex":0.000011000000000000001,"cache_read_input_token_cost":4.4e-7,"input_cost_per_token_priority":8.8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000044000000000000006,"cache_creation_input_token_cost":5.5e-6,"cache_read_input_token_cost_flex":2.2e-7,"cache_creation_input_token_cost_flex":2.7500000000000004e-6,"cache_read_input_token_cost_priority":8.8e-7,"input_cost_per_token_above_272k_tokens":8.8e-6,"output_cost_per_token_above_272k_tokens":0.000033,"cache_creation_input_token_cost_priority":0.000011000000000000001,"input_cost_per_token_above_272k_tokens_flex":4.4e-6,"output_cost_per_token_above_272k_tokens_flex":0.0000165,"cache_read_input_token_cost_above_272k_tokens":8.8e-7,"input_cost_per_token_above_272k_tokens_priority":0.0000176,"output_cost_per_token_above_272k_tokens_priority":0.000066,"cache_creation_input_token_cost_above_272k_tokens":0.000011,"cache_read_input_token_cost_above_272k_tokens_flex":4.4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.76e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000022000000000000003},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_token_flex":2.2e-6,"output_cost_per_token_flex":0.000011000000000000001,"cache_read_input_token_cost":4.4e-7,"input_cost_per_token_priority":8.8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000044000000000000006,"cache_creation_input_token_cost":5.5e-6,"cache_read_input_token_cost_flex":2.2e-7,"cache_creation_input_token_cost_flex":2.7500000000000004e-6,"cache_read_input_token_cost_priority":8.8e-7,"input_cost_per_token_above_272k_tokens":8.8e-6,"output_cost_per_token_above_272k_tokens":0.000033,"cache_creation_input_token_cost_priority":0.000011000000000000001,"input_cost_per_token_above_272k_tokens_flex":4.4e-6,"output_cost_per_token_above_272k_tokens_flex":0.0000165,"cache_read_input_token_cost_above_272k_tokens":8.8e-7,"input_cost_per_token_above_272k_tokens_priority":0.0000176,"output_cost_per_token_above_272k_tokens_priority":0.000066,"cache_creation_input_token_cost_above_272k_tokens":0.000011,"cache_read_input_token_cost_above_272k_tokens_flex":4.4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.76e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000022000000000000003},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.6-terra","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.0000132,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":6.6e-6,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":4.4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000264,"cache_creation_input_token_cost":2.75e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"cache_read_input_token_cost_priority":4.4e-7,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.000019800000000000004,"cache_creation_input_token_cost_priority":5.500000000000001e-6,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":9.900000000000002e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"input_cost_per_token_above_272k_tokens_priority":8.8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003960000000000001,"cache_creation_input_token_cost_above_272k_tokens":5.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000011000000000000001},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.0000132,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":6.6e-6,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":4.4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000264,"cache_creation_input_token_cost":2.75e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"cache_read_input_token_cost_priority":4.4e-7,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.000019800000000000004,"cache_creation_input_token_cost_priority":5.500000000000001e-6,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":9.900000000000002e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"input_cost_per_token_above_272k_tokens_priority":8.8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003960000000000001,"cache_creation_input_token_cost_above_272k_tokens":5.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000011000000000000001},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"list_pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.1","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5.1","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"list_pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5-mini","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":2.75e-8,"input_cost_per_token_priority":4.95e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.96e-6,"cache_read_input_token_cost_priority":4.9500000000000006e-8},"list_pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":2.75e-8,"input_cost_per_token_priority":4.95e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.96e-6,"cache_read_input_token_cost_priority":4.9500000000000006e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5-nano","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.5e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":5.5000000000000004e-9,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":5.5e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":5.5000000000000004e-9,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.6-flash","object":"model","created":1784646733,"owned_by":"vertex","model_name":"gemini-3.6-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_token_flex":3.75e-7,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"output_cost_per_token_flex":1.875e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.35e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":6.75e-6,"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_token_flex":3.75e-7,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"output_cost_per_token_flex":1.875e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.35e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":6.75e-6,"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.5-flash-lite","object":"model","created":1784646726,"owned_by":"vertex","model_name":"gemini-3.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":3e-7,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.5e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":1.5e-8,"cache_read_input_audio_token_cost":3e-8,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":3e-7,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.5e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":1.5e-8,"cache_read_input_audio_token_cost":3e-8,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.014},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-6-luna","object":"model","created":1783590864,"owned_by":"databricks","model_name":"databricks-gpt-5-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-5.6 Luna is the fast, cost-efficient model in OpenAI's GPT-5.6 family, bringing strong reasoning and agentic capability at the lowest cost in the lineup. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.9999e-7,"output_cost_per_token":1.20001e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":1.9999e-8,"input_cost_per_token_priority":3.9998e-7,"output_cost_per_token_priority":2.40002e-6,"cache_creation_input_token_cost":2.4997e-7,"input_cost_per_token_above_272k_tokens":3.9998e-7,"output_cost_per_token_above_272k_tokens":1.79998e-6,"cache_creation_input_token_cost_priority":5.0001e-7,"cache_read_input_token_cost_above_272k_tokens":3.997e-8,"input_cost_per_token_above_272k_tokens_priority":8.0003e-7,"output_cost_per_token_above_272k_tokens_priority":3.60003e-6,"cache_creation_input_token_cost_above_272k_tokens":5.0001e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8.001e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1.00002e-6},"list_pricing":{"input_cost_per_token":1.9999e-7,"output_cost_per_token":1.20001e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":1.9999e-8,"input_cost_per_token_priority":3.9998e-7,"output_cost_per_token_priority":2.40002e-6,"cache_creation_input_token_cost":2.4997e-7,"input_cost_per_token_above_272k_tokens":3.9998e-7,"output_cost_per_token_above_272k_tokens":1.79998e-6,"cache_creation_input_token_cost_priority":5.0001e-7,"cache_read_input_token_cost_above_272k_tokens":3.997e-8,"input_cost_per_token_above_272k_tokens_priority":8.0003e-7,"output_cost_per_token_above_272k_tokens_priority":3.60003e-6,"cache_creation_input_token_cost_above_272k_tokens":5.0001e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8.001e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1.00002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-6-terra","object":"model","created":1783590857,"owned_by":"databricks","model_name":"databricks-gpt-5-6-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-5.6 Terra is the balanced model in OpenAI's GPT-5.6 family for everyday agentic and reasoning workloads, offering performance competitive with GPT-5.5 at a lower cost. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.99997e-6,"output_cost_per_token":0.00001200003,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.000171429,"cache_read_input_token_cost":1.99997e-7,"input_cost_per_token_priority":4.00001e-6,"output_cost_per_token_priority":0.00002399999,"cache_creation_input_token_cost":2.49998e-6,"input_cost_per_token_above_272k_tokens":4.00001e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens":3.9998e-7,"input_cost_per_token_above_272k_tokens_priority":8.00002e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003600002,"cache_creation_input_token_cost_above_272k_tokens":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.0003e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":9.99999e-6},"list_pricing":{"input_cost_per_token":1.99997e-6,"output_cost_per_token":0.00001200003,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.000171429,"cache_read_input_token_cost":1.99997e-7,"input_cost_per_token_priority":4.00001e-6,"output_cost_per_token_priority":0.00002399999,"cache_creation_input_token_cost":2.49998e-6,"input_cost_per_token_above_272k_tokens":4.00001e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens":3.9998e-7,"input_cost_per_token_above_272k_tokens_priority":8.00002e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003600002,"cache_creation_input_token_cost_above_272k_tokens":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.0003e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":9.99999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-6-sol","object":"model","created":1783590850,"owned_by":"databricks","model_name":"databricks-gpt-5-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-5.6 Sol is OpenAI's flagship model in the GPT-5.6 family, delivering state-of-the-art performance on agentic coding, long-horizon reasoning, and complex tool use, with support for a new maximum reasoning effort. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.9999995e-6,"output_cost_per_token":0.0000199999996,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":3.9999995e-7,"cache_creation_input_token_cost":5.00003e-6,"input_cost_per_token_above_272k_tokens":8.00002e-6,"output_cost_per_token_above_272k_tokens":0.00003,"cache_creation_input_token_cost_priority":9.99999e-6,"cache_read_input_token_cost_above_272k_tokens":8.0003e-7,"input_cost_per_token_above_272k_tokens_priority":0.00001599997,"output_cost_per_token_above_272k_tokens_priority":0.00006000001,"cache_creation_input_token_cost_above_272k_tokens":9.99999e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.59999e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001999998},"list_pricing":{"input_cost_per_token":3.9999995e-6,"output_cost_per_token":0.0000199999996,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":3.9999995e-7,"cache_creation_input_token_cost":5.00003e-6,"input_cost_per_token_above_272k_tokens":8.00002e-6,"output_cost_per_token_above_272k_tokens":0.00003,"cache_creation_input_token_cost_priority":9.99999e-6,"cache_read_input_token_cost_above_272k_tokens":8.0003e-7,"input_cost_per_token_above_272k_tokens_priority":0.00001599997,"output_cost_per_token_above_272k_tokens_priority":0.00006000001,"cache_creation_input_token_cost_above_272k_tokens":9.99999e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.59999e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001999998},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-5","object":"model","created":1782843083,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-5","object":"model","created":1782843083,"owned_by":"vertex","model_name":"claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.1-flash-lite-image","object":"model","created":1782837225,"owned_by":"vertex","model_name":"gemini-3.1-flash-lite-image","context_length":65536,"max_input_tokens":null,"max_output_tokens":66000,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-2508","object":"model","created":1782745560,"owned_by":"mistral","model_name":"mistral-medium-2508","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-medium-2604","object":"model","created":1782745560,"owned_by":"mistral","model_name":"mistral-medium-2604","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/glm-5.2","object":"model","created":1782376549,"owned_by":"scaleway","model_name":"glm-5.2","context_length":256000,"max_input_tokens":null,"max_output_tokens":131072,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.014738934606051e-6,"output_cost_per_token":6.156146744629601e-6},"list_pricing":{"input_cost_per_token":2.014738934606051e-6,"output_cost_per_token":6.156146744629601e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-haiku-4-5-20251001-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-haiku-4-5-20251001-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"list_pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-5-20251101-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-5-20251101-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-6-v1","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-6-v1","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-4-5-20250929-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-4-5-20250929-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.pixtral-large-2502-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"mistral.pixtral-large-2502-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.1-flash-image","object":"model","created":1781754065,"owned_by":"vertex","model_name":"gemini-3.1-flash-image","context_length":131072,"max_input_tokens":null,"max_output_tokens":32768,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"output_cost_per_image_token":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"output_cost_per_image_token":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3-pro-image","object":"model","created":1781754054,"owned_by":"vertex","model_name":"gemini-3-pro-image","context_length":65536,"max_input_tokens":null,"max_output_tokens":32768,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":2e-7,"output_cost_per_image_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":2e-7,"output_cost_per_image_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/glm-5-2","object":"model","created":1781631930,"owned_by":"mistral","model_name":"glm-5-2","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"list_pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"databricks/databricks-gpt-5-4-nano","object":"model","created":1781107944,"owned_by":"databricks","model_name":"databricks-gpt-5-4-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5.4 Nano is a lightweight, cost-optimized large language model developed by OpenAI. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.9999e-7,"output_cost_per_token":1.24999e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017857,"cache_read_input_token_cost":1.9999e-8,"cache_creation_input_token_cost":1.9999e-7},"list_pricing":{"input_cost_per_token":1.9999e-7,"output_cost_per_token":1.24999e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017857,"cache_read_input_token_cost":1.9999e-8,"cache_creation_input_token_cost":1.9999e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-4-mini","object":"model","created":1781107854,"owned_by":"databricks","model_name":"databricks-gpt-5-4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5.4 Mini is a cost-optimized large language model developed by OpenAI. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7.4998e-7,"output_cost_per_token":4.50002e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.4998e-8,"input_cost_per_token_priority":1.50003e-6,"output_cost_per_token_priority":8.99997e-6,"cache_creation_input_token_cost":7.4998e-7,"cache_creation_input_token_cost_priority":1.50003e-6},"list_pricing":{"input_cost_per_token":7.4998e-7,"output_cost_per_token":4.50002e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.4998e-8,"input_cost_per_token_priority":1.50003e-6,"output_cost_per_token_priority":8.99997e-6,"cache_creation_input_token_cost":7.4998e-7,"cache_creation_input_token_cost_priority":1.50003e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-4","object":"model","created":1781107711,"owned_by":"databricks","model_name":"databricks-gpt-5-4","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-5.4 is a general purpose large language model with reasoning capabilities developed by OpenAI. It delivers improved performance on complex tasks with enhanced accuracy and more deliberate scaffolded reasoning. This model supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.49998e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.49998e-7,"input_cost_per_token_priority":5.00003e-6,"output_cost_per_token_priority":0.00002999997,"cache_creation_input_token_cost":2.49998e-6,"input_cost_per_token_above_272k_tokens":5.00003e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"cache_creation_input_token_cost_priority":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens":5.0001e-7,"input_cost_per_token_above_272k_tokens_priority":5.00003e-6,"output_cost_per_token_above_272k_tokens_priority":0.00002999997,"cache_read_input_token_cost_above_272k_tokens_priority":5.0001e-7},"list_pricing":{"input_cost_per_token":2.49998e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.49998e-7,"input_cost_per_token_priority":5.00003e-6,"output_cost_per_token_priority":0.00002999997,"cache_creation_input_token_cost":2.49998e-6,"input_cost_per_token_above_272k_tokens":5.00003e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"cache_creation_input_token_cost_priority":5.00003e-6,"cache_read_input_token_cost_above_272k_tokens":5.0001e-7,"input_cost_per_token_above_272k_tokens_priority":5.00003e-6,"output_cost_per_token_above_272k_tokens_priority":0.00002999997,"cache_read_input_token_cost_above_272k_tokens_priority":5.0001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-5","object":"model","created":1781107530,"owned_by":"databricks","model_name":"databricks-gpt-5-5","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"description":"GPT-5.5 is OpenAI's strongest frontier model for agentic work in enterprise, complex document reasoning, and long-horizon coding agents. GPT-5.5 also now powers Codex, OpenAI's coding agent. This model supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002999997,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000428571,"cache_read_input_token_cost":5.00003e-7,"input_cost_per_token_priority":0.00001249997,"output_cost_per_token_priority":0.0000750001,"cache_creation_input_token_cost":5.00003e-6,"input_cost_per_token_above_272k_tokens":9.99999e-6,"output_cost_per_token_above_272k_tokens":0.000045,"cache_creation_input_token_cost_priority":0.00001249997,"cache_read_input_token_cost_above_272k_tokens":1.00002e-6,"input_cost_per_token_above_272k_tokens_priority":0.00001249997,"output_cost_per_token_above_272k_tokens_priority":0.0000750001,"cache_read_input_token_cost_above_272k_tokens_priority":1.24999e-6},"list_pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002999997,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000428571,"cache_read_input_token_cost":5.00003e-7,"input_cost_per_token_priority":0.00001249997,"output_cost_per_token_priority":0.0000750001,"cache_creation_input_token_cost":5.00003e-6,"input_cost_per_token_above_272k_tokens":9.99999e-6,"output_cost_per_token_above_272k_tokens":0.000045,"cache_creation_input_token_cost_priority":0.00001249997,"cache_read_input_token_cost_above_272k_tokens":1.00002e-6,"input_cost_per_token_above_272k_tokens_priority":0.00001249997,"output_cost_per_token_above_272k_tokens_priority":0.0000750001,"cache_read_input_token_cost_above_272k_tokens_priority":1.24999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5","object":"model","created":1781007515,"owned_by":"vertex","model_name":"claude-fable-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":1.1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"list_pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":1.1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-sonnet-4-6","object":"model","created":1780933650,"owned_by":"databricks","model_name":"databricks-claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.99999e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":2.99999e-7,"cache_creation_input_token_cost":3.74997e-6,"cache_creation_input_token_cost_above_1hr":5.99998e-6},"list_pricing":{"input_cost_per_token":2.99999e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":2.99999e-7,"cache_creation_input_token_cost":3.74997e-6,"cache_creation_input_token_cost_above_1hr":5.99998e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-4-6","object":"model","created":1780933486,"owned_by":"databricks","model_name":"databricks-claude-opus-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Opus 4.6 is Anthropic's most capable hybrid reasoning model with adaptive thinking capabilities. This model introduces a new max effort level for the most demanding tasks, with high effort set as the default for optimal performance. Claude Opus 4.6 excels at complex reasoning, deep analysis, code generation, research, and sophisticated multi-step workflows. It features a 1 million token context window, making it ideal for enterprise applications that require both extensive analysis and comprehensive outputs. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6,"cache_creation_input_token_cost_above_1hr":9.99999e-6},"list_pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6,"cache_creation_input_token_cost_above_1hr":9.99999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-4-7","object":"model","created":1780933448,"owned_by":"databricks","model_name":"databricks-claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Opus 4.7 is Anthropic's most capable hybrid reasoning model, advancing the Opus series with improved accuracy, efficiency, and enhanced vision capabilities. This model delivers stronger performance on complex extraction and agentic reasoning tasks while using fewer output tokens than its predecessor. Claude Opus 4.7 features a 1 million token context window and increased image resolution support, making it ideal for enterprise applications that require deep analysis, document understanding, and sophisticated multi-step workflows. This model is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6,"cache_creation_input_token_cost_above_1hr":9.99999e-6},"list_pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6,"cache_creation_input_token_cost_above_1hr":9.99999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-4-8","object":"model","created":1780933263,"owned_by":"databricks","model_name":"databricks-claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Opus 4.8 is Anthropic's next-generation Opus model, hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6,"cache_creation_input_token_cost_above_1hr":9.99999e-6},"list_pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6,"cache_creation_input_token_cost_above_1hr":9.99999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"mistral/codestral-latest","object":"model","created":1780673223,"owned_by":"mistral","model_name":"codestral-latest","context_length":256000,"max_input_tokens":128000,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-tiny-latest","object":"model","created":1780673223,"owned_by":"mistral","model_name":"mistral-tiny-latest","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"list_pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"ovhcloud/Qwen3.5-397B-A17B","object":"model","created":1780673223,"owned_by":"ovhcloud","model_name":"Qwen3.5-397B-A17B","context_length":262144,"max_input_tokens":null,"max_output_tokens":65536,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.1e-7,"output_cost_per_token":4.25e-6},"list_pricing":{"input_cost_per_token":7.1e-7,"output_cost_per_token":4.25e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/Qwen3.5-9B","object":"model","created":1780673223,"owned_by":"ovhcloud","model_name":"Qwen3.5-9B","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":1.8e-7},"list_pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":1.8e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/Qwen3.6-27B","object":"model","created":1780673223,"owned_by":"ovhcloud","model_name":"Qwen3.6-27B","context_length":262144,"max_input_tokens":null,"max_output_tokens":65536,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.7e-7,"output_cost_per_token":3.19e-6},"list_pricing":{"input_cost_per_token":4.7e-7,"output_cost_per_token":3.19e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-8","object":"model","created":1779905091,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-4-8","object":"model","created":1779905091,"owned_by":"vertex","model_name":"claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.5-flash","object":"model","created":1779193800,"owned_by":"vertex","model_name":"gemini-3.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":3e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":4.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000162,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":9e-6,"cache_read_input_token_cost_flex":7.5e-8,"cache_read_input_audio_token_cost":3e-7,"cache_read_input_token_cost_priority":2.7e-7,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":3e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":4.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000162,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":9e-6,"cache_read_input_token_cost_flex":7.5e-8,"cache_read_input_audio_token_cost":3e-7,"cache_read_input_token_cost_priority":2.7e-7,"google_maps_grounding_cost_per_query":0.014},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.1-flash-lite","object":"model","created":1778168828,"owned_by":"vertex","model_name":"gemini-3.1-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":1.25e-7,"input_cost_per_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"output_cost_per_token_flex":7.5e-7,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.7e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":2.5e-7,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_audio_token_cost":5e-8,"input_cost_per_audio_token_priority":9e-7,"cache_read_input_token_cost_priority":4.5e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_flex":2.5e-8,"cache_read_input_audio_token_cost_priority":9e-8,"input_cost_per_audio_token_above_200k_tokens":5e-7,"input_cost_per_audio_token_above_200k_tokens_flex":2.5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":9e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":1.25e-7,"input_cost_per_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"output_cost_per_token_flex":7.5e-7,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.7e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":2.5e-7,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_audio_token_cost":5e-8,"input_cost_per_audio_token_priority":9e-7,"cache_read_input_token_cost_priority":4.5e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_flex":2.5e-8,"cache_read_input_audio_token_cost_priority":9e-8,"input_cost_per_audio_token_above_200k_tokens":5e-7,"input_cost_per_audio_token_above_200k_tokens_flex":2.5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":9e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/mistral-medium-3.5-128b","object":"model","created":1778158991,"owned_by":"scaleway","model_name":"mistral-medium-3.5-128b","context_length":256000,"max_input_tokens":null,"max_output_tokens":209715,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.6789491121717095e-6,"output_cost_per_token":8.394745560858547e-6},"list_pricing":{"input_cost_per_token":1.6789491121717095e-6,"output_cost_per_token":8.394745560858547e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/qwen3.6-35b-a3b","object":"model","created":1778158991,"owned_by":"scaleway","model_name":"qwen3.6-35b-a3b","context_length":256000,"max_input_tokens":null,"max_output_tokens":65536,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.798248520286182e-7,"output_cost_per_token":1.6789491121717095e-6},"list_pricing":{"input_cost_per_token":2.798248520286182e-7,"output_cost_per_token":1.6789491121717095e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-3-5","object":"model","created":1777570439,"owned_by":"mistral","model_name":"mistral-medium-3-5","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-medium-3.5","object":"model","created":1777570439,"owned_by":"mistral","model_name":"mistral-medium-3.5","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/gemma-4-26b-a4b-it","object":"model","created":1777469299,"owned_by":"scaleway","model_name":"gemma-4-26b-a4b-it","context_length":256000,"max_input_tokens":null,"max_output_tokens":32768,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.798248520286182e-7,"output_cost_per_token":5.596497040572364e-7},"list_pricing":{"input_cost_per_token":2.798248520286182e-7,"output_cost_per_token":5.596497040572364e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/codestral-2405","object":"model","created":1777389105,"owned_by":"mistral","model_name":"codestral-2405","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"description":"","source":"https://docs.mistral.ai/capabilities/code_generation/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":3.3e-6},"list_pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":3.3e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-large-2402","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-large-2402","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.0000132},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.0000132},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-medium-2312","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-medium-2312","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.9700000000000004e-6,"output_cost_per_token":8.910000000000001e-6},"list_pricing":{"input_cost_per_token":2.9700000000000004e-6,"output_cost_per_token":8.910000000000001e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-small","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-small","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-tiny","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-tiny","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"list_pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/open-mistral-7b","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mistral-7b","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"list_pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/open-mixtral-8x22b","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mixtral-8x22b","context_length":65336,"max_input_tokens":65336,"max_output_tokens":8191,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/open-mixtral-8x7b","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mixtral-8x7b","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.7e-7,"output_cost_per_token":7.7e-7},"list_pricing":{"input_cost_per_token":7.7e-7,"output_cost_per_token":7.7e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/pixtral-12b-2409","object":"model","created":1777389105,"owned_by":"mistral","model_name":"pixtral-12b-2409","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"description":"","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-7","object":"model","created":1776351100,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-4-7","object":"model","created":1776351100,"owned_by":"vertex","model_name":"claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/google/gemma-4-26b-a4b-it-maas","object":"model","created":1775227989,"owned_by":"vertex","model_name":"google/gemma-4-26b-a4b-it-maas","context_length":262144,"max_input_tokens":262144,"max_output_tokens":128000,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/minimax.minimax-m2.5","object":"model","created":1775193119,"owned_by":"amazon","model_name":"minimax.minimax-m2.5","context_length":196000,"max_input_tokens":196000,"max_output_tokens":8192,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.","source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"list_pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/nvidia.nemotron-super-3-120b","object":"model","created":1775193119,"owned_by":"amazon","model_name":"nvidia.nemotron-super-3-120b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":1.01e-6,"input_cost_per_token_flex":1.15e-7,"output_cost_per_token_flex":5.05e-7,"input_cost_per_token_priority":4.025e-7,"output_cost_per_token_priority":1.7675e-6},"list_pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":1.01e-6,"input_cost_per_token_flex":1.15e-7,"output_cost_per_token_flex":5.05e-7,"input_cost_per_token_priority":4.025e-7,"output_cost_per_token_priority":1.7675e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/zai.glm-5","object":"model","created":1775193119,"owned_by":"amazon","model_name":"zai.glm-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":131072,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":1.6e-6,"input_cost_per_token_priority":1.75e-6,"output_cost_per_token_priority":5.6e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":1.6e-6,"input_cost_per_token_priority":1.75e-6,"output_cost_per_token_priority":5.6e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-small-2603","object":"model","created":1773695685,"owned_by":"mistral","model_name":"mistral-small-2603","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/qwen3.5-397b-a17b","object":"model","created":1773394870,"owned_by":"scaleway","model_name":"qwen3.5-397b-a17b","context_length":250000,"max_input_tokens":null,"max_output_tokens":65536,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6.715796448686838e-7,"output_cost_per_token":4.029477869212102e-6},"list_pricing":{"input_cost_per_token":6.715796448686838e-7,"output_cost_per_token":4.029477869212102e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.devstral-2-123b","object":"model","created":1772697599,"owned_by":"amazon","model_name":"mistral.devstral-2-123b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":2e-7,"output_cost_per_token_flex":1e-6,"input_cost_per_token_priority":7e-7,"output_cost_per_token_priority":3.5e-6},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":2e-7,"output_cost_per_token_flex":1e-6,"input_cost_per_token_priority":7e-7,"output_cost_per_token_priority":3.5e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/zai.glm-4.7-flash","object":"model","created":1772697599,"owned_by":"amazon","model_name":"zai.glm-4.7-flash","context_length":203000,"max_input_tokens":203000,"max_output_tokens":128000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":2e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":7e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":2e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":7e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.mistral-7b-instruct-v0:2","object":"model","created":1772632546,"owned_by":"amazon","model_name":"mistral.mistral-7b-instruct-v0:2","context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.6e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.6e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.mistral-large-2402-v1:0","object":"model","created":1772632546,"owned_by":"amazon","model_name":"mistral.mistral-large-2402-v1:0","context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.2e-6,"output_cost_per_token":0.0000156},"list_pricing":{"input_cost_per_token":5.2e-6,"output_cost_per_token":0.0000156},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.mixtral-8x7b-instruct-v0:1","object":"model","created":1772632546,"owned_by":"amazon","model_name":"mistral.mixtral-8x7b-instruct-v0:1","context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.9e-7,"output_cost_per_token":9.1e-7},"list_pricing":{"input_cost_per_token":5.9e-7,"output_cost_per_token":9.1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/devstral-latest","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-latest","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":"https://mistral.ai/news/devstral-2-vibe-cli","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/devstral-medium-latest","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-medium-latest","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":"https://mistral.ai/news/devstral-2-vibe-cli","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/devstral-small-latest","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-small-latest","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"description":"","source":"https://docs.mistral.ai/models/devstral-small-2-25-12","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-4-6","object":"model","created":1771342990,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-4-6","object":"model","created":1771342990,"owned_by":"vertex","model_name":"claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/deepseek.v3.2","object":"model","created":1770991619,"owned_by":"amazon","model_name":"deepseek.v3.2","context_length":156000,"max_input_tokens":156000,"max_output_tokens":8000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7.4e-7,"output_cost_per_token":2.22e-6,"input_cost_per_token_flex":3.7e-7,"output_cost_per_token_flex":1.11e-6,"input_cost_per_token_priority":1.295e-6,"output_cost_per_token_priority":3.885e-6},"list_pricing":{"input_cost_per_token":7.4e-7,"output_cost_per_token":2.22e-6,"input_cost_per_token_flex":3.7e-7,"output_cost_per_token_flex":1.11e-6,"input_cost_per_token_priority":1.295e-6,"output_cost_per_token_priority":3.885e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/minimax.minimax-m2.1","object":"model","created":1770991619,"owned_by":"amazon","model_name":"minimax.minimax-m2.1","context_length":196000,"max_input_tokens":196000,"max_output_tokens":8192,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development.","source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"list_pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/nvidia.nemotron-nano-3-30b","object":"model","created":1770991619,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-3-30b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4.2e-7},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4.2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/zai.glm-4.7","object":"model","created":1770991619,"owned_by":"amazon","model_name":"zai.glm-4.7","context_length":203000,"max_input_tokens":203000,"max_output_tokens":131072,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"input_cost_per_token_flex":3e-7,"output_cost_per_token_flex":1.1e-6,"input_cost_per_token_priority":1.05e-6,"output_cost_per_token_priority":3.85e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"input_cost_per_token_flex":3e-7,"output_cost_per_token_flex":1.1e-6,"input_cost_per_token_priority":1.05e-6,"output_cost_per_token_priority":3.85e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-4-6","object":"model","created":1770219050,"owned_by":"vertex","model_name":"claude-opus-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-claude-haiku-4-5","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-claude-haiku-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost efficient hybrid reasoning model, optimized for real-time use and high-volume workloads. It features two modes: quick responses for time-sensitive interactions and extended reasoning for complex problem-solving. Haiku 4.5 excels in environments like coding assistance, automated agent workflows, and enterprise-scale analysis. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.00002e-6,"output_cost_per_token":5.00003e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1.00002e-7,"cache_creation_input_token_cost":1.24999e-6,"cache_creation_input_token_cost_above_1hr":1.99997e-6},"list_pricing":{"input_cost_per_token":1.00002e-6,"output_cost_per_token":5.00003e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1.00002e-7,"cache_creation_input_token_cost":1.24999e-6,"cache_creation_input_token_cost_above_1hr":1.99997e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-4-5","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-claude-opus-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"description":"Claude Opus 4.5 is a large language model built and trained by Anthropic for production software engineering and sophisticated multi-tool agents. It supports text and image input with a 200K token context window. The model is designed for professional tasks requiring complex reasoning across multiple systems, including code generation, document creation, spreadsheets, presentations, and multi-step agent workflows. It features advanced tool use capabilities including tool search and programmatic tool calling for agents working with large tool libraries. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]},"supports_output_config":true},"pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6,"cache_creation_input_token_cost_above_1hr":9.99999e-6},"list_pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6,"cache_creation_input_token_cost_above_1hr":9.99999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-sonnet-4-5","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-claude-sonnet-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"description":"Claude Sonnet 4.5 is Anthropic's most advanced hybrid reasoning model. It offers two modes: near-instant responses and extended thinking for deeper reasoning based on the complexity of the task. Claude Sonnet 4.5 specializes in application that require a balance of practical throughput and advanced thinking such as customer-facing agents, production coding workflows, and content generation at scale. This endpoint is hosted by Databricks","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.99999e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":2.99999e-7,"cache_creation_input_token_cost":3.74997e-6,"cache_creation_input_token_cost_above_1hr":5.99998e-6},"list_pricing":{"input_cost_per_token":2.99999e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":2.99999e-7,"cache_creation_input_token_cost":3.74997e-6,"cache_creation_input_token_cost_above_1hr":5.99998e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gemma-3-12b","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gemma-3-12b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":32000,"description":"Gemma 3 12B is a state-of-the-art multimodal language model built and trained by Google. The model supports a context length of 128K tokens and can analyze images and text. With support for over 140 languages and optimized for dialogue use cases, Gemma 3 12B is aligned with human preferences for helpfulness and safety. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":5.0001e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"list_pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":5.0001e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5 is a state-of-the-art, general purpose large language model and reasoning model built and trained by OpenAI. It supports multimodal inputs and features a 128K token context window. The model is built for coding, chat, reasoning and agent-driven tasks. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.24999e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.24999e-7,"input_cost_per_token_priority":2.49998e-6,"output_cost_per_token_priority":0.00001999998,"cache_creation_input_token_cost":1.24999e-6,"cache_creation_input_token_cost_priority":2.49998e-6},"list_pricing":{"input_cost_per_token":1.24999e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.24999e-7,"input_cost_per_token_priority":2.49998e-6,"output_cost_per_token_priority":0.00001999998,"cache_creation_input_token_cost":1.24999e-6,"cache_creation_input_token_cost_priority":2.49998e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-1","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-1","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5.1 is a general purpose large language model with reasoning capabilities developed by OpenAI. This model features both Instant and Thinking modes for fast conversation or deep reasoning, automatically adjusting for simple or complex tasks. The model excels at content creation, tutoring, technical support, and coding, with less reliance on strict prompt engineering than prior versions. It supports multimodal inputs and features a 128K token context window. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.24999e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.24999e-7,"input_cost_per_token_priority":2.49998e-6,"output_cost_per_token_priority":0.00001999998,"cache_creation_input_token_cost":1.24999e-6,"cache_creation_input_token_cost_priority":2.49998e-6},"list_pricing":{"input_cost_per_token":1.24999e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.24999e-7,"input_cost_per_token_priority":2.49998e-6,"output_cost_per_token_priority":0.00001999998,"cache_creation_input_token_cost":1.24999e-6,"cache_creation_input_token_cost_priority":2.49998e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-mini","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5 mini is a state-of-the-art, general purpose large language model and reasoning model built and trained by OpenAI. It supports multimodal inputs and features a 128K token context window. The model is cost-optimized for reasoning and chat workloads and excels at well-defined tasks that require reliable reasoning, precise language, and rapid output for text and images. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.4997e-7,"output_cost_per_token":1.99997e-6,"input_dbu_cost_per_token":3.571e-6,"output_dbu_cost_per_token":0.000028571,"cache_read_input_token_cost":2.4997e-8,"input_cost_per_token_priority":4.5003e-7,"output_cost_per_token_priority":3.60003e-6,"cache_creation_input_token_cost":2.4997e-7,"cache_creation_input_token_cost_priority":4.5003e-7},"list_pricing":{"input_cost_per_token":2.4997e-7,"output_cost_per_token":1.99997e-6,"input_dbu_cost_per_token":3.571e-6,"output_dbu_cost_per_token":0.000028571,"cache_read_input_token_cost":2.4997e-8,"input_cost_per_token_priority":4.5003e-7,"output_cost_per_token_priority":3.60003e-6,"cache_creation_input_token_cost":2.4997e-7,"cache_creation_input_token_cost_priority":4.5003e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-nano","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"description":"GPT-5 nano is a state-of-the-art, general purpose large language model and reasoning model built and trained by OpenAI. It supports multimodal inputs and features a 128K token context window. The model excels at high-throughput tasks like simple instruction-following or classification for routine business processes or mobile applications. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4.998e-8,"output_cost_per_token":3.9998e-7,"input_dbu_cost_per_token":7.14e-7,"output_dbu_cost_per_token":5.714000000000001e-6,"cache_read_input_token_cost":4.998e-9,"cache_creation_input_token_cost":4.998e-8},"list_pricing":{"input_cost_per_token":4.998e-8,"output_cost_per_token":3.9998e-7,"input_dbu_cost_per_token":7.14e-7,"output_dbu_cost_per_token":5.714000000000001e-6,"cache_read_input_token_cost":4.998e-9,"cache_creation_input_token_cost":4.998e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-oss-120b","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"description":"GPT OSS 120B is a state-of-the-art, reasoning model with chain-of-thought and adjustable reasoning effort levels built and trained by OpenAI. It is OpenAI's flagship open-weight model that features a 128K token context window. The model is built for high-quality reasoning tasks.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":5.9997e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":8.571e-6,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"list_pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":5.9997e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":8.571e-6,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-oss-20b","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-oss-20b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"description":"GPT OSS 20B is a state-of-the-art, lightweight reasoning model built and trained by OpenAI. This model also has a 128K token context window and excels at real-time copilots and batch inference tasks.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3.0002e-7,"input_dbu_cost_per_token":1e-6,"output_dbu_cost_per_token":4.285999999999999e-6,"cache_read_input_token_cost":7e-9,"cache_creation_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3.0002e-7,"input_dbu_cost_per_token":1e-6,"output_dbu_cost_per_token":4.285999999999999e-6,"cache_read_input_token_cost":7e-9,"cache_creation_input_token_cost":7e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-llama-4-maverick","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-llama-4-maverick","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"description":"Llama 4 Maverick is a state-of-the-art mixture of experts (MoE) language model trained and released by Meta. The model has 17B active parameters, 128 experts, and 400 billion total parameters. The model supports a context length of 128K tokens. The model is optimized for multilingual dialogue use cases, supporting 12 languages, and is aligned with human preferences for helpfulness and safety. It is not intended for use in languages other than English. Llama 4 is licensed under the Meta Llama 4 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Customers are responsible for ensuring compliance with applicable model licenses.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.0001e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5.0001e-8,"cache_creation_input_token_cost":5.0001e-7},"list_pricing":{"input_cost_per_token":5.0001e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5.0001e-8,"cache_creation_input_token_cost":5.0001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-meta-llama-3-3-70b-instruct","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-meta-llama-3-3-70b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"description":"Llama 3.3 is a state-of-the-art 70B parameter dense language model trained and released by Meta. The model supports a context length of 128K tokens. The model is optimized for multilingual dialogue use cases and aligned with human preferences for helpfulness and safety. It is not intended for use in languages other than English. Meta Llama 3.3 is licensed under the Meta Llama 3.3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Customers are responsible for ensuring compliance with applicable model licenses.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.0001e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5.0001e-8,"cache_creation_input_token_cost":5.0001e-7},"list_pricing":{"input_cost_per_token":5.0001e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5.0001e-8,"cache_creation_input_token_cost":5.0001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"ovhcloud/gpt-oss-120b","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"gpt-oss-120b","context_length":131072,"max_input_tokens":131000,"max_output_tokens":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":"https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.7e-7},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.7e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/gpt-oss-20b","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"gpt-oss-20b","context_length":131072,"max_input_tokens":131000,"max_output_tokens":null,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.","source":"https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":1.8e-7},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":1.8e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/Meta-Llama-3_3-70B-Instruct","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"Meta-Llama-3_3-70B-Instruct","context_length":131072,"max_input_tokens":131000,"max_output_tokens":null,"description":null,"source":"https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7.4e-7,"output_cost_per_token":7.4e-7},"list_pricing":{"input_cost_per_token":7.4e-7,"output_cost_per_token":7.4e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/Mistral-Small-3.2-24B-Instruct-2506","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"Mistral-Small-3.2-24B-Instruct-2506","context_length":131072,"max_input_tokens":128000,"max_output_tokens":null,"description":null,"source":"https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3.1e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3.1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/Qwen2.5-VL-72B-Instruct","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"Qwen2.5-VL-72B-Instruct","context_length":32768,"max_input_tokens":32000,"max_output_tokens":null,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","source":"https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.01e-6,"output_cost_per_token":1.01e-6},"list_pricing":{"input_cost_per_token":1.01e-6,"output_cost_per_token":1.01e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/moonshotai.kimi-k2.5","object":"model","created":1769487076,"owned_by":"amazon","model_name":"moonshotai.kimi-k2.5","context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm.","source":"https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/google.gemma-3-12b-it","object":"model","created":1767692616,"owned_by":"amazon","model_name":"google.gemma-3-12b-it","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":2.9e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.6e-7,"output_cost_per_token_priority":5.1e-7},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":2.9e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.6e-7,"output_cost_per_token_priority":5.1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/google.gemma-3-27b-it","object":"model","created":1767692616,"owned_by":"amazon","model_name":"google.gemma-3-27b-it","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":3.8e-7,"input_cost_per_token_flex":1.2e-7,"output_cost_per_token_flex":1.9e-7,"input_cost_per_token_priority":4e-7,"output_cost_per_token_priority":6.7e-7},"list_pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":3.8e-7,"input_cost_per_token_flex":1.2e-7,"output_cost_per_token_flex":1.9e-7,"input_cost_per_token_priority":4e-7,"output_cost_per_token_priority":6.7e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/google.gemma-3-4b-it","object":"model","created":1767692616,"owned_by":"amazon","model_name":"google.gemma-3-4b-it","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":8e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":4e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":1.4e-7},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":8e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":4e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":1.4e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/minimax.minimax-m2","object":"model","created":1767692616,"owned_by":"amazon","model_name":"minimax.minimax-m2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":8000,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":1.5e-7,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":5.2e-7,"output_cost_per_token_priority":2.1e-6},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":1.5e-7,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":5.2e-7,"output_cost_per_token_priority":2.1e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.magistral-small-2509","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.magistral-small-2509","context_length":128000,"max_input_tokens":128000,"max_output_tokens":40000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":2.5e-7,"output_cost_per_token_flex":7.5e-7,"input_cost_per_token_priority":8.8e-7,"output_cost_per_token_priority":2.63e-6},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":2.5e-7,"output_cost_per_token_flex":7.5e-7,"input_cost_per_token_priority":8.8e-7,"output_cost_per_token_priority":2.63e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.ministral-3-14b-instruct","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-14b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":3.5e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":3.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.ministral-3-3b-instruct","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-3b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":5e-8,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":1.7e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":5e-8,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":1.7e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.ministral-3-8b-instruct","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-8b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":7e-8,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.6e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":7e-8,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.6e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.voxtral-mini-3b-2507","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.voxtral-mini-3b-2507","context_length":32768,"max_input_tokens":32768,"max_output_tokens":8192,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":2e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":7e-8},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":2e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":7e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.voxtral-small-24b-2507","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.voxtral-small-24b-2507","context_length":32768,"max_input_tokens":32768,"max_output_tokens":26214,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.","source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":5.2e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":5.2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/nvidia.nemotron-nano-12b-v2","object":"model","created":1767692616,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-12b-v2","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/nvidia.nemotron-nano-9b-v2","object":"model","created":1767692616,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-9b-v2","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.3e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4e-7},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.3e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-oss-120b-1:0","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-120b-1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-oss-20b-1:0","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-20b-1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":5.25e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":5.25e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-oss-safeguard-120b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-safeguard-120b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-oss-safeguard-20b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-safeguard-20b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":1.2e-7,"output_cost_per_token_priority":3.5e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":1.2e-7,"output_cost_per_token_priority":3.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/qwen.qwen3-32b-v1:0","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-32b-v1:0","context_length":32768,"max_input_tokens":32768,"max_output_tokens":8192,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/qwen.qwen3-coder-30b-a3b-v1:0","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-coder-30b-a3b-v1:0","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/qwen.qwen3-next-80b-a3b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-next-80b-a3b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.1e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.1e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/qwen.qwen3-vl-235b-a22b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-vl-235b-a22b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.3e-7,"output_cost_per_token":2.66e-6,"input_cost_per_token_priority":9.3e-7,"output_cost_per_token_priority":4.66e-6},"list_pricing":{"input_cost_per_token":5.3e-7,"output_cost_per_token":2.66e-6,"input_cost_per_token_priority":9.3e-7,"output_cost_per_token_priority":4.66e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/labs-devstral-small-2512","object":"model","created":1767692616,"owned_by":"mistral","model_name":"labs-devstral-small-2512","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"description":"","source":"https://docs.mistral.ai/models/devstral-small-2-25-12","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/magistral-medium-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"magistral-medium-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":null,"source":"https://mistral.ai/news/magistral","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/magistral-small-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"magistral-small-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":null,"source":"https://mistral.ai/pricing#api-pricing","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-medium","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-medium-2505","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium-2505","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-medium-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-small-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-small-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"description":null,"source":"https://mistral.ai/pricing","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/open-mistral-nemo","object":"model","created":1767692616,"owned_by":"mistral","model_name":"open-mistral-nemo","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":"https://mistral.ai/technology/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":3.3e-7},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":3.3e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/open-mistral-nemo-2407","object":"model","created":1767692616,"owned_by":"mistral","model_name":"open-mistral-nemo-2407","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"description":null,"source":"https://mistral.ai/technology/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":3.3e-7},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":3.3e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/devstral-2-123b-instruct-2512","object":"model","created":1766496679,"owned_by":"scaleway","model_name":"devstral-2-123b-instruct-2512","context_length":200000,"max_input_tokens":null,"max_output_tokens":16384,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.593999547491045e-7,"output_cost_per_token":2.296999773745522e-6},"list_pricing":{"input_cost_per_token":4.593999547491045e-7,"output_cost_per_token":2.296999773745522e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/devstral-2512","object":"model","created":1765285419,"owned_by":"mistral","model_name":"devstral-2512","context_length":262144,"max_input_tokens":null,"max_output_tokens":209715,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.","source":"https://mistral.ai/news/devstral-2-vibe-cli","capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":4.4000000000000004e-8},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":4.4000000000000004e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"amazon/amazon.nova-2-lite-v1:0","object":"model","created":1764696672,"owned_by":"amazon","model_name":"amazon.nova-2-lite-v1:0","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65535,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.","source":null,"capabilities":{"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":5.25e-7,"output_cost_per_token_priority":4.375e-6,"cache_read_input_token_cost_priority":1.3125e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":5.25e-7,"output_cost_per_token_priority":4.375e-6,"cache_read_input_token_cost_priority":1.3125e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/ministral-14b-2512","object":"model","created":1764681735,"owned_by":"mistral","model_name":"ministral-14b-2512","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-7,"cache_read_input_token_cost":2.2000000000000002e-8,"input_cost_per_token_batches":1.1e-7,"output_cost_per_token_batches":1.1e-7,"cache_read_input_token_cost_batches":1.1000000000000001e-8},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-7,"cache_read_input_token_cost":2.2000000000000002e-8,"input_cost_per_token_batches":1.1e-7,"output_cost_per_token_batches":1.1e-7,"cache_read_input_token_cost_batches":1.1000000000000001e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/ministral-8b-2512","object":"model","created":1764681654,"owned_by":"mistral","model_name":"ministral-8b-2512","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","source":"https://mistral.ai/pricing","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/ministral-3b-2512","object":"model","created":1764681560,"owned_by":"mistral","model_name":"ministral-3b-2512","context_length":131072,"max_input_tokens":131072,"max_output_tokens":104857,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":1.1e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":1.1e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-large-2512","object":"model","created":1764624472,"owned_by":"mistral","model_name":"mistral-large-2512","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","source":"https://docs.mistral.ai/models/mistral-large-3-25-12","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.5e-7,"output_cost_per_token":1.65e-6,"cache_read_input_token_cost":5.5e-8,"input_cost_per_token_batches":2.75e-7,"output_cost_per_token_batches":8.25e-7,"cache_read_input_token_cost_batches":2.75e-8},"list_pricing":{"input_cost_per_token":5.5e-7,"output_cost_per_token":1.65e-6,"cache_read_input_token_cost":5.5e-8,"input_cost_per_token_batches":2.75e-7,"output_cost_per_token_batches":8.25e-7,"cache_read_input_token_cost_batches":2.75e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"vertex/claude-opus-4-5","object":"model","created":1764010580,"owned_by":"vertex","model_name":"claude-opus-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-haiku-4-5","object":"model","created":1760547638,"owned_by":"vertex","model_name":"claude-haiku-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"list_pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-2.5-flash-image","object":"model","created":1759870431,"owned_by":"vertex","model_name":"gemini-2.5-flash-image","context_length":32768,"max_input_tokens":null,"max_output_tokens":8192,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":3e-7,"cache_read_input_token_cost":3e-8,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_audio_token_cost":1e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":3e-7,"cache_read_input_token_cost":3e-8,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_audio_token_cost":1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-4-5","object":"model","created":1759161676,"owned_by":"vertex","model_name":"claude-sonnet-4-5","context_length":1000000,"max_input_tokens":200000,"max_output_tokens":64000,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/gpt-oss-120b","object":"model","created":1755093042,"owned_by":"scaleway","model_name":"gpt-oss-120b","context_length":128000,"max_input_tokens":null,"max_output_tokens":32768,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.6789491121717094e-7,"output_cost_per_token":6.715796448686838e-7},"list_pricing":{"input_cost_per_token":1.6789491121717094e-7,"output_cost_per_token":6.715796448686838e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/holo2-30b-a3b","object":"model","created":1755006551,"owned_by":"scaleway","model_name":"holo2-30b-a3b","context_length":22000,"max_input_tokens":null,"max_output_tokens":32768,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.4604989808830504e-7,"output_cost_per_token":8.074497622060451e-7},"list_pricing":{"input_cost_per_token":3.4604989808830504e-7,"output_cost_per_token":8.074497622060451e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/mistral-small-3.2-24b-instruct-2506","object":"model","created":1755006551,"owned_by":"scaleway","model_name":"mistral-small-3.2-24b-instruct-2506","context_length":128000,"max_input_tokens":null,"max_output_tokens":32768,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.6789491121717094e-7,"output_cost_per_token":3.917547928400655e-7},"list_pricing":{"input_cost_per_token":1.6789491121717094e-7,"output_cost_per_token":3.917547928400655e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/qwen3-coder-30b-a3b-instruct","object":"model","created":1755006551,"owned_by":"scaleway","model_name":"qwen3-coder-30b-a3b-instruct","context_length":128000,"max_input_tokens":null,"max_output_tokens":32768,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.24499898413796e-7,"output_cost_per_token":8.97999593655184e-7},"list_pricing":{"input_cost_per_token":2.24499898413796e-7,"output_cost_per_token":8.97999593655184e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/codestral-2508","object":"model","created":1754079630,"owned_by":"mistral","model_name":"codestral-2508","context_length":256000,"max_input_tokens":128000,"max_output_tokens":204800,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.","source":"https://mistral.ai/news/codestral-25-08","capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/qwen3-235b-a22b-instruct-2507","object":"model","created":1754049528,"owned_by":"scaleway","model_name":"qwen3-235b-a22b-instruct-2507","context_length":250000,"max_input_tokens":null,"max_output_tokens":16384,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":8.394745560858547e-7,"output_cost_per_token":2.518423668257564e-6},"list_pricing":{"input_cost_per_token":8.394745560858547e-7,"output_cost_per_token":2.518423668257564e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-2.5-flash-lite","object":"model","created":1753200276,"owned_by":"vertex","model_name":"gemini-2.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.","source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_flex":5e-8,"input_cost_per_audio_token":3e-7,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":1.8e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":7.2e-7,"input_cost_per_audio_token_flex":5e-8,"output_cost_per_reasoning_token":4e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_audio_token_cost":3e-8,"input_cost_per_audio_token_priority":5.4e-7,"cache_read_input_token_cost_priority":1.8e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":5.4e-8,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-8,"input_cost_per_audio_token_above_200k_tokens_priority":5.4e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_flex":5e-8,"input_cost_per_audio_token":3e-7,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":1.8e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":7.2e-7,"input_cost_per_audio_token_flex":5e-8,"output_cost_per_reasoning_token":4e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_audio_token_cost":3e-8,"input_cost_per_audio_token_priority":5.4e-7,"cache_read_input_token_cost_priority":1.8e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":5.4e-8,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-8,"input_cost_per_audio_token_above_200k_tokens_priority":5.4e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-2.5-flash","object":"model","created":1750172488,"owned_by":"vertex","model_name":"gemini-2.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":null,"capabilities":{"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":1e-6,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":4.5e-6,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":3e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":1.8e-7,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":1.8e-6},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":1e-6,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":4.5e-6,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":3e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":1.8e-7,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":1.8e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-2.5-pro","object":"model","created":1750169544,"owned_by":"vertex","model_name":"gemini-2.5-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":0.000018,"cache_read_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":2.25e-7,"google_maps_grounding_cost_per_query":0.025,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":0.000015,"input_cost_per_token_above_200k_tokens_flex":1.25e-6,"output_cost_per_token_above_200k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"input_cost_per_token_above_200k_tokens_priority":4.5e-6,"output_cost_per_token_above_200k_tokens_priority":0.000027,"cache_creation_input_token_cost_above_200k_tokens":2.5e-7,"cache_read_input_token_cost_above_200k_tokens_priority":4.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":0.000018,"cache_read_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":2.25e-7,"google_maps_grounding_cost_per_query":0.025,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":0.000015,"input_cost_per_token_above_200k_tokens_flex":1.25e-6,"output_cost_per_token_above_200k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"input_cost_per_token_above_200k_tokens_priority":4.5e-6,"output_cost_per_token_above_200k_tokens_priority":0.000027,"cache_creation_input_token_cost_above_200k_tokens":2.5e-7,"cache_read_input_token_cost_above_200k_tokens_priority":4.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-3","object":"model","created":1746627341,"owned_by":"mistral","model_name":"mistral-medium-3","context_length":262144,"max_input_tokens":262144,"max_output_tokens":104857,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":4.4000000000000004e-8},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":4.4000000000000004e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"qwen/qwen-plus","object":"model","created":1738409840,"owned_by":"qwen","model_name":"qwen-plus","context_length":1000000,"max_input_tokens":995904,"max_output_tokens":32768,"description":"The Plus model of the Qwen3 series, effectively integrates thinking mode and non-thinking mode, allowing for mode switching during conversations. Its reasoning capabilities significantly surpass those of QwQ, and its general capabilities notably exceed those of Qwen2.5-Plus, reaching the SOTA level in the same scale within the industry.","source":"https://www.alibabacloud.com/help/en/model-studio/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7,"output_cost_per_reasoning_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":2.34e-6,"cache_read_input_token_cost":1.56e-7,"cache_creation_input_token_cost":9.75e-7,"output_cost_per_reasoning_token":7.8e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7,"output_cost_per_reasoning_token":2.6e-6},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":8e-8,"cache_creation_input_token_cost":5e-7,"output_cost_per_reasoning_token":4e-6},{"range":[256000,1000000],"input_cost_per_token":1.2e-6,"output_cost_per_token":3.6000000000000003e-6,"cache_read_input_token_cost":2.4e-7,"cache_creation_input_token_cost":1.5e-6,"output_cost_per_reasoning_token":0.000012}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":8e-8,"cache_creation_input_token_cost":5e-7,"output_cost_per_reasoning_token":4e-6},"discount":0.35,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"qwen/qwen-plus-2025-12-01","object":"model","created":1738409840,"owned_by":"qwen","model_name":"qwen-plus-2025-12-01","context_length":1000000,"max_input_tokens":997952,"max_output_tokens":32768,"description":"This version is a snapshot as of December 1, 2025, and features improved reasoning capabilities compared to the July 28 snapshot. Agent capabilities and multi-turn tool invocation abilities have been further enhanced, and performance on subjective creative tasks has improved significantly. It supports a context length of up to 1 million tokens, with tiered pricing based on context length.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":2.34e-6,"output_cost_per_reasoning_token":7.8e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"output_cost_per_reasoning_token":4e-6},{"range":[256000,1000000],"input_cost_per_token":1.2e-6,"output_cost_per_token":3.6000000000000003e-6,"output_cost_per_reasoning_token":0.000012}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"output_cost_per_reasoning_token":4e-6},"discount":0.35,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/llama-3.3-70b-instruct","object":"model","created":1736258559,"owned_by":"scaleway","model_name":"llama-3.3-70b-instruct","context_length":128000,"max_input_tokens":null,"max_output_tokens":16384,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.0073694673030256e-6,"output_cost_per_token":1.0073694673030256e-6},"list_pricing":{"input_cost_per_token":1.0073694673030256e-6,"output_cost_per_token":1.0073694673030256e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.nova-lite-v1:0","object":"model","created":1733437363,"owned_by":"amazon","model_name":"amazon.nova-lite-v1:0","context_length":300000,"max_input_tokens":300000,"max_output_tokens":5120,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output.","source":null,"capabilities":{"input_modalities":["text","image","file","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.nova-micro-v1:0","object":"model","created":1733437237,"owned_by":"amazon","model_name":"amazon.nova-micro-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":5120,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.5e-8,"output_cost_per_token":1.4e-7,"cache_read_input_token_cost":8.75e-9},"list_pricing":{"input_cost_per_token":3.5e-8,"output_cost_per_token":1.4e-7,"cache_read_input_token_cost":8.75e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.nova-pro-v1:0","object":"model","created":1733436303,"owned_by":"amazon","model_name":"amazon.nova-pro-v1:0","context_length":300000,"max_input_tokens":300000,"max_output_tokens":5120,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks.","source":null,"capabilities":{"input_modalities":["text","image","file","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":8e-7,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":4e-7,"output_cost_per_token_flex":1.6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":1.4e-6,"output_cost_per_token_priority":5.6e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_priority":3.5e-7},"list_pricing":{"input_cost_per_token":8e-7,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":4e-7,"output_cost_per_token_flex":1.6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":1.4e-6,"output_cost_per_token_priority":5.6e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_priority":3.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-large-2407","object":"model","created":1731978415,"owned_by":"mistral","model_name":"mistral-large-2407","context_length":131072,"max_input_tokens":null,"max_output_tokens":104857,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more.","source":null,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"cache_read_input_token_cost":2.2e-7},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"cache_read_input_token_cost":2.2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/gemma-3-27b-it","object":"model","created":1730385501,"owned_by":"scaleway","model_name":"gemma-3-27b-it","context_length":40000,"max_input_tokens":null,"max_output_tokens":8192,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.8712497171819026e-7,"output_cost_per_token":5.742499434363805e-7},"list_pricing":{"input_cost_per_token":2.8712497171819026e-7,"output_cost_per_token":5.742499434363805e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/pixtral-12b-2409","object":"model","created":1730385501,"owned_by":"scaleway","model_name":"pixtral-12b-2409","context_length":128000,"max_input_tokens":null,"max_output_tokens":4096,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.24499898413796e-7,"output_cost_per_token":2.24499898413796e-7},"list_pricing":{"input_cost_per_token":2.24499898413796e-7,"output_cost_per_token":2.24499898413796e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/ministral-8b-latest","object":"model","created":1729123200,"owned_by":"mistral","model_name":"ministral-8b-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":102400,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/mistral-large-latest","object":"model","created":1708905600,"owned_by":"mistral","model_name":"mistral-large-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":102400,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more.","source":"https://docs.mistral.ai/models/mistral-large-3-25-12","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"cache_read_input_token_cost":2.2e-7},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"cache_read_input_token_cost":2.2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"vertex/gemini-pro-latest","object":"model","created":1791907477,"owned_by":"vertex","model_name":"gemini-4-argon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.875e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1e-7,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_audio_token":4e-6,"input_cost_per_image_token":4e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.00002,"cache_read_input_audio_token_cost":2e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":"vertex/gemini-4-argon"},{"id":"mistral/mistral-large-4","object":"model","created":1791294122,"owned_by":"mistral","model_name":"mistral-large-4-0","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":262144,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":2.1e-6,"cache_read_input_token_cost":7e-8,"input_cost_per_token_batches":3.5e-7,"output_cost_per_token_batches":1.05e-6,"cache_read_input_token_cost_batches":3.5e-8},"list_pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":2.1e-6,"cache_read_input_token_cost":7e-8,"input_cost_per_token_batches":3.5e-7,"output_cost_per_token_batches":1.05e-6,"cache_read_input_token_cost_batches":3.5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":"mistral/mistral-large-4-0"},{"id":"vertex/gemini-flash-latest","object":"model","created":1788362056,"owned_by":"vertex","model_name":"gemini-3.8-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"cache_read_input_token_cost":7.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_audio_token_cost":7.5e-8,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":8.33333333333334e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_audio_token_cost":1.5e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":"vertex/gemini-3.8-flash"}]}