[ { "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": false, "model_id": "allenai/olmOCR-7B-0725-FP8", "model_name": "OlmOCR 7B 0725 FP8", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.27, "output_cost_per_million": 1.5, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "supports_tool_choice": true, "model_id": "anthropic/claude-3-7-sonnet-latest", "model_name": "Claude 3.7 Sonnet", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.0000825, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "supports_tool_choice": true, "model_id": "anthropic/claude-4-opus", "model_name": "Claude 4 Opus", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 16.5, "output_cost_per_million": 82.5, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.00000215, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1-0528", "model_name": "DeepSeek R1 0528", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.5, "output_cost_per_million": 2.1500000000000004, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1-0528-Turbo", "model_name": "DeepSeek R1 0528 Turbo", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 1, "output_cost_per_million": 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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": false, "model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "model_name": "DeepSeek R1 Distill Llama 70B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.19999999999999998, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 2.7e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "model_name": "DeepSeek R1 Distill Qwen 32B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.27, "output_cost_per_million": 0.27, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1-Turbo", "model_name": "DeepSeek R1 Turbo", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 1, "output_cost_per_million": 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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 8.8e-7, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-V3-0324", "model_name": "DeepSeek V3 0324", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.25, "output_cost_per_million": 0.88, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-V3.1-Terminus", "model_name": "DeepSeek V3.1 Terminus", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.27, "output_cost_per_million": 1, "cache_read_cost_per_token": 2.16e-7, "cache_read_cost_per_million": 0.216, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "deprecation_date": "2026-06-01", "max_tokens": 1000000, "supports_tool_choice": true, "model_id": "google/gemini-2.0-flash-001", "model_name": "Gemini 2.0 Flash 001", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "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", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "google/gemma-3-12b-it", "model_name": "Gemma 3 12B It", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.049999999999999996, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 9e-8, "output_cost_per_token": 1.6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "google/gemma-3-27b-it", "model_name": "Gemma 3 27B It", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.09, "output_cost_per_million": 0.16, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-8, "output_cost_per_token": 8e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "google/gemma-3-4b-it", "model_name": "Gemma 3 4B It", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.04, "output_cost_per_million": 0.08, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 9e-8, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "Gryphe/MythoMax-L2-13b", "model_name": "MythoMax L2 13B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.08, "output_cost_per_million": 0.09, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 4.9e-8, "output_cost_per_token": 4.9e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": false, "model_id": "meta-llama/Llama-3.2-11B-Vision-Instruct", "model_name": "Llama 3.2 11B Vision Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.049, "output_cost_per_million": 0.049, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-8, "output_cost_per_token": 2e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "meta-llama/Llama-3.2-3B-Instruct", "model_name": "Llama 3.2 3B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.02, "output_cost_per_million": 0.02, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.3e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "meta-llama/Llama-3.3-70B-Instruct", "model_name": "Llama 3.3 70B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.22999999999999998, "output_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5.5e-8, "output_cost_per_token": 5.5e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": false, "model_id": "meta-llama/Llama-Guard-3-8B", "model_name": "Llama Guard 3 8B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.055, "output_cost_per_million": 0.055, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 1.8e-7, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_tool_choice": false, "model_id": "meta-llama/Llama-Guard-4-12B", "model_name": "Llama Guard 4 12B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.18, "output_cost_per_million": 0.18, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-8, "output_cost_per_token": 6e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3-8B-Instruct", "model_name": "Meta Llama 3 8B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.03, "output_cost_per_million": 0.06, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3.1-70B-Instruct", "model_name": "Meta Llama 3.1 70B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-8, "output_cost_per_token": 5e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "model_name": "Meta Llama 3.1 8B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.03, "output_cost_per_million": 0.049999999999999996, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 1.4e-7, "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "model_id": "microsoft/phi-4", "model_name": "Phi 4", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.07, "output_cost_per_million": 0.14, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 4.8e-7, "output_cost_per_token": 4.8e-7, "max_input_tokens": 65536, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": false, "model_id": "microsoft/WizardLM-2-8x22B", "model_name": "WizardLM 2 8x22B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.48, "output_cost_per_million": 0.48, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-8, "output_cost_per_token": 4e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "mistralai/Mistral-Nemo-Instruct-2407", "model_name": "Mistral Nemo Instruct (Jul 2024)", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.02, "output_cost_per_million": 0.04, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "model_name": "Mistral Small 3.2 24B Instruct (Jun 2025)", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.075, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "NousResearch/Hermes-3-Llama-3.1-405B", "model_name": "Hermes 3 Llama 3.1 405B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 1, "output_cost_per_million": 1, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": false, "model_id": "NousResearch/Hermes-3-Llama-3.1-70B", "model_name": "Hermes 3 Llama 3.1 70B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.3, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct", "model_name": "Llama 3.1 Nemotron 70B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "nvidia/Llama-3.3-Nemotron-Super-49B-v1.5", "model_name": "Llama 3.3 Nemotron Super 49B V1.5", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-8, "output_cost_per_token": 1.6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "nvidia/NVIDIA-Nemotron-Nano-9B-v2", "model_name": "NVIDIA Nemotron Nano 9B V2", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.04, "output_cost_per_million": 0.16, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3.9e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "Qwen/Qwen2.5-72B-Instruct", "model_name": "Qwen2.5 72B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.12, "output_cost_per_million": 0.39, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 4e-8, "output_cost_per_token": 1e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": false, "model_id": "Qwen/Qwen2.5-7B-Instruct", "model_name": "Qwen2.5 7B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.04, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "Qwen/Qwen2.5-VL-32B-Instruct", "model_name": "Qwen2.5 VL 32B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.19999999999999998, "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_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7, "max_input_tokens": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-14B", "model_name": "Qwen3 14B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.06, "output_cost_per_million": 0.24, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 5.4e-7, "max_input_tokens": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-235B-A22B", "model_name": "Qwen3 235B A22B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.18, "output_cost_per_million": 0.54, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 9e-8, "output_cost_per_token": 6e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "model_name": "Qwen3 235B A22B Instruct (Jul 2025)", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.09, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 2.9e-7, "max_input_tokens": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-30B-A3B", "model_name": "Qwen3 30B A3B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.08, "output_cost_per_million": 0.29, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-32B", "model_name": "Qwen3 32B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.28, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "model_name": "Qwen3 Coder 480B A35B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.9e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "model_name": "Qwen3 Coder 480B A35B Instruct Turbo", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.29, "output_cost_per_million": 1.2, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "Qwen/QwQ-32B", "model_name": "QwQ 32B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.15, "output_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 4e-8, "output_cost_per_token": 5e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": false, "model_id": "Sao10K/L3-8B-Lunaris-v1-Turbo", "model_name": "L3 8B Lunaris V1 Turbo", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.04, "output_cost_per_million": 0.049999999999999996, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 7.5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": false, "model_id": "Sao10K/L3.1-70B-Euryale-v2.2", "model_name": "L3.1 70B Euryale V2.2", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.65, "output_cost_per_million": 0.75, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 7.5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": false, "model_id": "Sao10K/L3.3-70B-Euryale-v2.3", "model_name": "L3.3 70B Euryale V2.3", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.65, "output_cost_per_million": 0.75, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "zai-org/GLM-4.5", "model_name": "GLM 4.5", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false } ]