[ { "input_cost_per_token": 7.7e-7, "output_cost_per_token": 7.7e-7, "model_id": "baseten/deepseek-ai/DeepSeek-V3-0324", "model_name": "DeepSeek V3 0324", "provider_id": "baseten", "provider_name": "Baseten", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.77, "output_cost_per_million": 0.77, "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": 5e-7, "output_cost_per_token": 0.0000015, "model_id": "baseten/deepseek-ai/DeepSeek-V3.1", "model_name": "DeepSeek V3.1", "provider_id": "baseten", "provider_name": "Baseten", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.5, "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 }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "model_id": "baseten/MiniMaxAI/MiniMax-M2.5", "model_name": "MiniMax M2.5", "provider_id": "baseten", "provider_name": "Baseten", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.3, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "model_id": "baseten/moonshotai/Kimi-K2-Instruct-0905", "model_name": "Kimi K2 Instruct (May 2009)", "provider_id": "baseten", "provider_name": "Baseten", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "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 }, { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "model_id": "baseten/moonshotai/Kimi-K2-Thinking", "model_name": "Kimi K2 Thinking", "provider_id": "baseten", "provider_name": "Baseten", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "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 }, { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003, "model_id": "baseten/moonshotai/Kimi-K2.5", "model_name": "Kimi K2.5", "provider_id": "baseten", "provider_name": "Baseten", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.6, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 7.5e-7, "model_id": "baseten/nvidia/Nemotron-120B-A12B", "model_name": "Nemotron 120B A12B", "provider_id": "baseten", "provider_name": "Baseten", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.3, "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": 1e-7, "output_cost_per_token": 5e-7, "model_id": "baseten/openai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "baseten", "provider_name": "Baseten", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.5, "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 }, { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "model_id": "baseten/zai-org/GLM-4.6", "model_name": "GLM 4.6", "provider_id": "baseten", "provider_name": "Baseten", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "model_id": "baseten/zai-org/GLM-4.7", "model_name": "GLM 4.7", "provider_id": "baseten", "provider_name": "Baseten", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.00000315, "model_id": "baseten/zai-org/GLM-5", "model_name": "GLM 5", "provider_id": "baseten", "provider_name": "Baseten", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.95, "output_cost_per_million": 3.15, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false } ]