[
  {
    "supports_function_calling": true,
    "supports_parallel_function_calling": true,
    "supports_response_schema": true,
    "input_cost_per_token": 3.5e-7,
    "output_cost_per_token": 7.5e-7,
    "max_input_tokens": 131072,
    "max_output_tokens": 32768,
    "max_tokens": 32768,
    "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras",
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "model_id": "cerebras/gpt-oss-120b",
    "model_name": "GPT Oss 120B",
    "provider_id": "cerebras",
    "provider_name": "Cerebras",
    "input_cost_per_million": 0.35,
    "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_json_mode": true,
    "supports_parallel_functions": true,
    "supports_vision": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 8.5e-7,
    "output_cost_per_token": 0.0000012,
    "max_input_tokens": 128000,
    "max_output_tokens": 128000,
    "max_tokens": 128000,
    "supports_tool_choice": true,
    "model_id": "cerebras/llama-3.3-70b",
    "model_name": "Llama 3.3 70B",
    "provider_id": "cerebras",
    "provider_name": "Cerebras",
    "input_cost_per_million": 0.85,
    "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": 6e-7,
    "output_cost_per_token": 6e-7,
    "max_input_tokens": 128000,
    "max_output_tokens": 128000,
    "max_tokens": 128000,
    "supports_tool_choice": true,
    "model_id": "cerebras/llama3.1-70b",
    "model_name": "Llama 3.1 70B",
    "provider_id": "cerebras",
    "provider_name": "Cerebras",
    "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": 1e-7,
    "max_input_tokens": 128000,
    "max_output_tokens": 128000,
    "max_tokens": 128000,
    "supports_tool_choice": true,
    "model_id": "cerebras/llama3.1-8b",
    "model_name": "Llama 3.1 8B",
    "provider_id": "cerebras",
    "provider_name": "Cerebras",
    "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_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": 128000,
    "max_output_tokens": 128000,
    "max_tokens": 128000,
    "source": "https://inference-docs.cerebras.ai/support/pricing",
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "model_id": "cerebras/qwen-3-32b",
    "model_name": "Qwen 3 32B",
    "provider_id": "cerebras",
    "provider_name": "Cerebras",
    "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",
    "deprecation_date": null,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 0.00000225,
    "output_cost_per_token": 0.00000275,
    "max_input_tokens": 128000,
    "max_output_tokens": 128000,
    "deprecation_date": "2026-01-20",
    "max_tokens": 128000,
    "source": "https://www.cerebras.ai/pricing",
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "model_id": "cerebras/zai-glm-4.6",
    "model_name": "Zai Glm 4.6",
    "provider_id": "cerebras",
    "provider_name": "Cerebras",
    "input_cost_per_million": 2.25,
    "output_cost_per_million": 2.75,
    "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",
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 0.00000225,
    "output_cost_per_token": 0.00000275,
    "max_input_tokens": 128000,
    "max_output_tokens": 128000,
    "max_tokens": 128000,
    "source": "https://www.cerebras.ai/pricing",
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "model_id": "cerebras/zai-glm-4.7",
    "model_name": "Zai Glm 4.7",
    "provider_id": "cerebras",
    "provider_name": "Cerebras",
    "input_cost_per_million": 2.25,
    "output_cost_per_million": 2.75,
    "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_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  }
]