[
  {
    "input_cost_per_pixel": 1.3e-9,
    "output_cost_per_pixel": 0,
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models",
    "supported_endpoints": [
      "/v1/images/generations"
    ],
    "model_id": "nscale/black-forest-labs/FLUX.1-schnell",
    "model_name": "FLUX.1 Schnell",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "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": "image",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 3.75e-7,
    "output_cost_per_token": 3.75e-7,
    "metadata": {
      "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output."
    },
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
    "model_name": "DeepSeek R1 Distill Llama 70B",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "input_cost_per_million": 0.375,
    "output_cost_per_million": 0.375,
    "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": 2.5e-8,
    "output_cost_per_token": 2.5e-8,
    "metadata": {
      "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output."
    },
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
    "model_name": "DeepSeek R1 Distill Llama 8B",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "input_cost_per_million": 0.024999999999999998,
    "output_cost_per_million": 0.024999999999999998,
    "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": 9e-8,
    "output_cost_per_token": 9e-8,
    "metadata": {
      "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output."
    },
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
    "model_name": "DeepSeek R1 Distill Qwen 1.5B",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "input_cost_per_million": 0.09,
    "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_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 7e-8,
    "output_cost_per_token": 7e-8,
    "metadata": {
      "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output."
    },
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
    "model_name": "DeepSeek R1 Distill Qwen 14B",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "input_cost_per_million": 0.07,
    "output_cost_per_million": 0.07,
    "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": 1.5e-7,
    "output_cost_per_token": 1.5e-7,
    "metadata": {
      "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output."
    },
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
    "model_name": "DeepSeek R1 Distill Qwen 32B",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "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_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 2e-7,
    "output_cost_per_token": 2e-7,
    "metadata": {
      "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
    },
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
    "model_name": "DeepSeek R1 Distill Qwen 7B",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "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_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 3e-8,
    "output_cost_per_token": 3e-8,
    "metadata": {
      "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output."
    },
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/meta-llama/Llama-3.1-8B-Instruct",
    "model_name": "Llama 3.1 8B Instruct",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "input_cost_per_million": 0.03,
    "output_cost_per_million": 0.03,
    "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": 2e-7,
    "output_cost_per_token": 2e-7,
    "metadata": {
      "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
    },
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/meta-llama/Llama-3.3-70B-Instruct",
    "model_name": "Llama 3.3 70B Instruct",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "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_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 9e-8,
    "output_cost_per_token": 2.9e-7,
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct",
    "model_name": "Llama 4 Scout 17B 16E Instruct",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "input_cost_per_million": 0.09,
    "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_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 6e-7,
    "output_cost_per_token": 6e-7,
    "metadata": {
      "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output."
    },
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/mistralai/mixtral-8x22b-instruct-v0.1",
    "model_name": "Mixtral 8x22B Instruct V0.1",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "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_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 6e-8,
    "output_cost_per_token": 2e-7,
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/Qwen/Qwen2.5-Coder-32B-Instruct",
    "model_name": "Qwen2.5 Coder 32B Instruct",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "input_cost_per_million": 0.06,
    "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_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 1e-8,
    "output_cost_per_token": 3e-8,
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/Qwen/Qwen2.5-Coder-3B-Instruct",
    "model_name": "Qwen2.5 Coder 3B Instruct",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "input_cost_per_million": 0.01,
    "output_cost_per_million": 0.03,
    "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-8,
    "output_cost_per_token": 3e-8,
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/Qwen/Qwen2.5-Coder-7B-Instruct",
    "model_name": "Qwen2.5 Coder 7B Instruct",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "input_cost_per_million": 0.01,
    "output_cost_per_million": 0.03,
    "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": 2e-7,
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
    "model_id": "nscale/Qwen/QwQ-32B",
    "model_name": "QwQ 32B",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "max_input_tokens": 0,
    "max_output_tokens": 0,
    "input_cost_per_million": 0.18,
    "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_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_pixel": 3e-9,
    "output_cost_per_pixel": 0,
    "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models",
    "supported_endpoints": [
      "/v1/images/generations"
    ],
    "model_id": "nscale/stabilityai/stable-diffusion-xl-base-1.0",
    "model_name": "Stable Diffusion Xl Base 1.0",
    "provider_id": "nscale",
    "provider_name": "Nscale",
    "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": "image",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  }
]