[ { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 0.0005, "output_cost_per_token": 0.002, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "model_id": "watsonx/bigscience/mt0-xxl-13b", "model_name": "Mt0 Xxl 13B", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 500, "output_cost_per_million": 2000, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 0.0005, "output_cost_per_token": 0.002, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "model_id": "watsonx/core42/jais-13b-chat", "model_name": "Jais 13B Chat", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 500, "output_cost_per_million": 2000, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "model_id": "watsonx/google/flan-t5-xl-3b", "model_name": "Flan T5 Xl 3B", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.6, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "model_id": "watsonx/ibm/granite-13b-chat-v2", "model_name": "Granite 13B Chat V2", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.6, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "model_id": "watsonx/ibm/granite-13b-instruct-v2", "model_name": "Granite 13B Instruct V2", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.6, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "model_id": "watsonx/ibm/granite-3-3-8b-instruct", "model_name": "Granite 3 3 8B Instruct", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "supports_audio_input": false, "supports_audio_output": false, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "watsonx/ibm/granite-3-8b-instruct", "model_name": "Granite 3 8B Instruct", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 6e-8, "output_cost_per_token": 2.5e-7, "max_input_tokens": 20480, "max_output_tokens": 20480, "max_tokens": 20480, "model_id": "watsonx/ibm/granite-4-h-small", "model_name": "Granite 4 H Small", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.06, "output_cost_per_million": 0.25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "model_id": "watsonx/ibm/granite-guardian-3-2-2b", "model_name": "Granite Guardian 3 2 2B", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.09999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "model_id": "watsonx/ibm/granite-guardian-3-3-8b", "model_name": "Granite Guardian 3 3 8B", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 3.8e-7, "output_cost_per_token": 3.8e-7, "max_input_tokens": 512, "max_output_tokens": 512, "max_tokens": 512, "model_id": "watsonx/ibm/granite-ttm-1024-96-r2", "model_name": "Granite Ttm 1024 96 R2", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.38, "output_cost_per_million": 0.38, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 3.8e-7, "output_cost_per_token": 3.8e-7, "max_input_tokens": 512, "max_output_tokens": 512, "max_tokens": 512, "model_id": "watsonx/ibm/granite-ttm-1536-96-r2", "model_name": "Granite Ttm 1536 96 R2", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.38, "output_cost_per_million": 0.38, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 3.8e-7, "output_cost_per_token": 3.8e-7, "max_input_tokens": 512, "max_output_tokens": 512, "max_tokens": 512, "model_id": "watsonx/ibm/granite-ttm-512-96-r2", "model_name": "Granite Ttm 512 96 R2", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.38, "output_cost_per_million": 0.38, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "model_id": "watsonx/ibm/granite-vision-3-2-2b", "model_name": "Granite Vision 3 2 2B", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.09999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 3.5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "model_id": "watsonx/meta-llama/llama-3-2-11b-vision-instruct", "model_name": "Llama 3 2 11B Vision Instruct", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.35, "output_cost_per_million": 0.35, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "model_id": "watsonx/meta-llama/llama-3-2-1b-instruct", "model_name": "Llama 3 2 1B Instruct", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.09999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "model_id": "watsonx/meta-llama/llama-3-2-3b-instruct", "model_name": "Llama 3 2 3B Instruct", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.15, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "model_id": "watsonx/meta-llama/llama-3-2-90b-vision-instruct", "model_name": "Llama 3 2 90B Vision Instruct", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 2, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 7.1e-7, "output_cost_per_token": 7.1e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "model_id": "watsonx/meta-llama/llama-3-3-70b-instruct", "model_name": "Llama 3 3 70B Instruct", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.71, "output_cost_per_million": 0.71, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.0000014, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "model_id": "watsonx/meta-llama/llama-4-maverick-17b", "model_name": "Llama 4 Maverick 17B", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.35, "output_cost_per_million": 1.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 3.5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "model_id": "watsonx/meta-llama/llama-guard-3-11b-vision", "model_name": "Llama Guard 3 11B Vision", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.35, "output_cost_per_million": 0.35, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.00001, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "supports_audio_input": false, "supports_audio_output": false, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "watsonx/mistralai/mistral-large", "model_name": "Mistral Large", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 3, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "model_id": "watsonx/mistralai/mistral-medium-2505", "model_name": "Mistral Medium (May 2025)", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 3, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "model_id": "watsonx/mistralai/mistral-small-2503", "model_name": "Mistral Small (Mar 2025)", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "model_id": "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503", "model_name": "Mistral Small 3 1 24B Instruct (Mar 2025)", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 3.5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "model_id": "watsonx/mistralai/pixtral-12b-2409", "model_name": "Pixtral 12B (Sep 2024)", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.35, "output_cost_per_million": 0.35, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "model_id": "watsonx/openai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.0000018, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "model_id": "watsonx/sdaia/allam-1-13b-instruct", "model_name": "Allam 1 13B Instruct", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 1.7999999999999998, "output_cost_per_million": 1.7999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "watsonx/whisper-large-v3-turbo", "model_name": "Whisper Large V3 Turbo", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false } ]