[ { "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000007, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/DeepSeek-R1", "model_name": "DeepSeek R1", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 5, "output_cost_per_million": 7, "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": 7e-7, "output_cost_per_token": 0.0000014, "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecation_date": "2026-03-20", "max_tokens": 131072, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/DeepSeek-R1-Distill-Llama-70B", "model_name": "DeepSeek R1 Distill Llama 70B", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.7, "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", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.0000045, "max_input_tokens": 32768, "max_output_tokens": 32768, "deprecation_date": "2026-04-14", "max_tokens": 32768, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "sambanova/DeepSeek-V3-0324", "model_name": "DeepSeek V3 0324", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 3, "output_cost_per_million": 4.5, "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", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.0000045, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/DeepSeek-V3.1", "model_name": "DeepSeek V3.1", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 3, "output_cost_per_million": 4.5, "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": 0.000003, "output_cost_per_token": 0.0000045, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/DeepSeek-V3.2", "model_name": "DeepSeek V3.2", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 3, "output_cost_per_million": 4.5, "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_vision": true, "input_cost_per_token": 3.8e-7, "output_cost_per_token": 0.00000115, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/gemma-4-31B-it", "model_name": "Gemma 4 31B It", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.38, "output_cost_per_million": 1.15, "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_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 5.9e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.22, "output_cost_per_million": 0.59, "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, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6.3e-7, "output_cost_per_token": 0.0000018, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_tool_choice": true, "model_id": "sambanova/Llama-4-Maverick-17B-128E-Instruct", "model_name": "Llama 4 Maverick 17B 128E Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.63, "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_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 7e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "deprecation_date": "2025-06-19", "max_tokens": 8192, "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_tool_choice": true, "model_id": "sambanova/Llama-4-Scout-17B-16E-Instruct", "model_name": "Llama 4 Scout 17B 16E Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 0.7, "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_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00001, "max_input_tokens": 16384, "max_output_tokens": 16384, "deprecation_date": "2025-06-25", "max_tokens": 16384, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_tool_choice": true, "model_id": "sambanova/Meta-Llama-3.1-405B-Instruct", "model_name": "Meta Llama 3.1 405B Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 5, "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", "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 16384, "max_output_tokens": 16384, "deprecation_date": "2026-04-14", "max_tokens": 16384, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_tool_choice": true, "model_id": "sambanova/Meta-Llama-3.1-8B-Instruct", "model_name": "Meta Llama 3.1 8B Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.09999999999999999, "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", "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "input_cost_per_token": 4e-8, "output_cost_per_token": 8e-8, "max_input_tokens": 16384, "max_output_tokens": 16384, "deprecation_date": "2025-06-25", "max_tokens": 16384, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/Meta-Llama-3.2-1B-Instruct", "model_name": "Meta Llama 3.2 1B Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "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", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-8, "output_cost_per_token": 1.6e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "deprecation_date": "2025-06-25", "max_tokens": 4096, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/Meta-Llama-3.2-3B-Instruct", "model_name": "Meta Llama 3.2 3B Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.08, "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", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_tool_choice": true, "model_id": "sambanova/Meta-Llama-3.3-70B-Instruct", "model_name": "Meta Llama 3.3 70B Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.6, "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_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 16384, "max_output_tokens": 16384, "deprecation_date": "2025-06-25", "max_tokens": 16384, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/Meta-Llama-Guard-3-8B", "model_name": "Meta Llama Guard 3 8B", "provider_id": "sambanova", "provider_name": "Sambanova", "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", "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": 0.0000024, "max_input_tokens": 196608, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "sambanova/MiniMax-M2.7", "model_name": "MiniMax M2.7", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0001, "max_input_tokens": 4096, "max_output_tokens": 4096, "deprecation_date": "2025-06-19", "max_tokens": 4096, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_audio_input": true, "model_id": "sambanova/Qwen2-Audio-7B-Instruct", "model_name": "Qwen2 Audio 7B Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.5, "output_cost_per_million": 100, "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_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": 8e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "deprecation_date": "2026-04-06", "max_tokens": 8192, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "sambanova/Qwen3-32B", "model_name": "Qwen3 32B", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 0.7999999999999999, "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 }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 16384, "max_output_tokens": 16384, "deprecation_date": "2025-06-25", "max_tokens": 16384, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/QwQ-32B", "model_name": "QwQ 32B", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.5, "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", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false } ]