Deepseek Ai

{
  "id": "deepseek-ai/deepseek-coder-6.7b-instruct",
  "name": "deepseek-ai/deepseek-coder-6.7b-instruct",
  "description": "",
  "context_length": null
}

{
  "name": "deepseek-v4.1-flash",
  "publisher": "deepseek-ai",
  "labels": [
    "B200",
    "Together AI",
    "H100 NVL",
    "CoreWeave",
    "H200 NVL",
    "GB300",
    "Vision Language Model",
    "GB200",
    "Baseten",
    "Deepinfra",
    "Multimodal MOE",
    "chat",
    "KV Cache Optimization",
    "H200",
    "Download Available",
    "Partner Endpoint",
    "Free Endpoint",
    "OpenRouter",
    "Causal Encoder Decoder",
    "GMI Cloud",
    "B300 SXM6 AC",
    "H100 80GB HBM3"
  ],
  "attributes": {
    "AVAILABLE": "true",
    "last_month_download_count": "8071",
    "lastMonthApiInvocationCount": "2793940",
    "lastMonthDownloadCount": "8063",
    "logo": "https://assets.ngc.nvidia.com/products/api-catalog/images/deepseek-v4_1-flash.jpg",
    "PREVIEW": "true",
    "last_month_api_invocation_count": "4450598"
  },
  "id": "deepseek-ai/deepseek-v4.1-flash",
  "description": "552B MoE, 8B active params with native multimodal support and lower API cost using smaller KV cache",
  "context_length": null
}

{
  "id": "@cf/deepseek-ai/deepseek-v4-flash-0731",
  "source": 1,
  "name": "@cf/deepseek-ai/deepseek-v4-flash-0731",
  "description": "DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities.",
  "task": {
    "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34",
    "name": "Text Generation",
    "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."
  },
  "created_at": "2026-07-31 14:10:43.440",
  "tags": [],
  "properties": [
    {
      "property_id": "async_queue",
      "value": "true"
    },
    {
      "property_id": "require_workers_paid",
      "value": "true"
    },
    {
      "property_id": "context_window",
      "value": "1048576"
    },
    {
      "property_id": "function_calling",
      "value": "true"
    },
    {
      "property_id": "reasoning",
      "value": "true"
    },
    {
      "property_id": "reasoning_effort",
      "value": {
        "supported_efforts": [
          "max",
          "high",
          "low",
          "none"
        ],
        "default_effort": "high",
        "default_enabled": true,
        "mandatory": false,
        "normalizes_to": {
          "null": "high",
          "minimal": "low",
          "medium": "high",
          "xhigh": "high"
        }
      }
    },
    {
      "property_id": "price",
      "value": [
        {
          "unit": "per M input tokens",
          "price": 0.44,
          "currency": "USD"
        },
        {
          "unit": "per M output tokens",
          "price": 1.32,
          "currency": "USD"
        },
        {
          "unit": "per M cached input tokens",
          "price": 0.014,
          "currency": "USD"
        }
      ]
    }
  ],
  "context_length": 1048576
}

{
  "id": "@cf/deepseek-ai/deepseek-v4-pro-0813",
  "source": 1,
  "name": "@cf/deepseek-ai/deepseek-v4-pro-0813",
  "description": "DeepSeek V4 Pro is a high-capability reasoning model from DeepSeek with a one million token context window, built for long-horizon agentic workflows and…",
  "task": {
    "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34",
    "name": "Text Generation",
    "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."
  },
  "created_at": "2026-08-13 17:15:08.489",
  "tags": [],
  "properties": [
    {
      "property_id": "require_workers_paid",
      "value": "true"
    },
    {
      "property_id": "context_window",
      "value": "1048576"
    },
    {
      "property_id": "function_calling",
      "value": "true"
    },
    {
      "property_id": "reasoning",
      "value": "true"
    },
    {
      "property_id": "reasoning_effort",
      "value": {
        "supported_efforts": [
          "max",
          "high",
          "low",
          "none"
        ],
        "default_effort": "high",
        "default_enabled": true,
        "mandatory": false,
        "normalizes_to": {
          "null": "high",
          "minimal": "low",
          "medium": "high",
          "xhigh": "high"
        }
      }
    },
    {
      "property_id": "price",
      "value": [
        {
          "unit": "per M input tokens",
          "price": 1.32,
          "currency": "USD"
        },
        {
          "unit": "per M output tokens",
          "price": 3.96,
          "currency": "USD"
        },
        {
          "unit": "per M cached input tokens",
          "price": 0.044,
          "currency": "USD"
        }
      ]
    }
  ],
  "context_length": 1048576
}

{
  "id": "@cf/deepseek-ai/deepseek-v4.1-flash-1017",
  "source": 1,
  "name": "@cf/deepseek-ai/deepseek-v4.1-flash-1017",
  "description": "We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million…",
  "task": {
    "id": "c329a1f9-323d-4e91-b2aa-582dd4188d34",
    "name": "Text Generation",
    "description": "Family of generative text models, such as large language models (LLM), that can be adapted for a variety of natural language tasks."
  },
  "created_at": "2026-10-17 03:51:20.275",
  "tags": [],
  "properties": [
    {
      "property_id": "require_workers_paid",
      "value": "true"
    },
    {
      "property_id": "context_window",
      "value": "1048576"
    },
    {
      "property_id": "function_calling",
      "value": "true"
    },
    {
      "property_id": "hugging_face_id",
      "value": "deepseek-ai/DeepSeek-V4.1-Flash-1017"
    },
    {
      "property_id": "openrouter_slug",
      "value": "deepseek/deepseek-v4.1-flash-1017"
    },
    {
      "property_id": "reasoning",
      "value": "true"
    },
    {
      "property_id": "reasoning_effort",
      "value": {
        "supported_efforts": [
          "max",
          "high",
          "low",
          "none"
        ],
        "default_effort": "high",
        "default_enabled": true,
        "mandatory": false,
        "normalizes_to": {
          "null": "high",
          "auto": "high",
          "minimal": "none",
          "medium": "high",
          "xhigh": "max"
        }
      }
    },
    {
      "property_id": "terms",
      "value": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/blob/main/LICENSE"
    },
    {
      "property_id": "vision",
      "value": "true"
    },
    {
      "property_id": "price",
      "value": [
        {
          "unit": "per M input tokens",
          "price": 0.3,
          "currency": "USD"
        },
        {
          "unit": "per M output tokens",
          "price": 1.2,
          "currency": "USD"
        },
        {
          "unit": "per M cached input tokens",
          "price": 0.006,
          "currency": "USD"
        }
      ]
    }
  ],
  "context_length": 1048576
}