{
  "page": "https://opencode.ai/data/deepseek/deepseek-v4-1-flash-1017",
  "updatedAt": null,
  "summary": "DeepSeek V4.1 Flash 1017 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens.",
  "model": {
    "id": "deepseek/deepseek-v4.1-flash-1017",
    "name": "DeepSeek V4.1 Flash 1017",
    "lab": "deepseek",
    "labName": "DeepSeek",
    "family": "deepseek-flash",
    "description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
    "releaseDate": "2026-10-17",
    "lastUpdated": "2026-10-17",
    "knowledgeCutoff": "2025-05",
    "contextTokens": 1000000,
    "outputTokens": 384000,
    "inputModalities": [
      "text",
      "image"
    ],
    "outputModalities": [
      "text"
    ],
    "reasoning": true,
    "toolCall": true,
    "openWeights": true,
    "weights": [
      {
        "label": "Hugging Face",
        "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      }
    ],
    "priceUsdPer1M": {
      "input": 0.3,
      "output": 1.2,
      "cachedInput": 0.006,
      "cacheWrite": 0.3
    },
    "benchmarks": [
      {
        "name": "Humanity's Last Exam",
        "score": 42.6,
        "variant": "without tools",
        "dataset": "full set",
        "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      },
      {
        "name": "Humanity's Last Exam",
        "score": 44,
        "variant": "without tools",
        "dataset": "text-only subset",
        "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      },
      {
        "name": "Terminal-Bench",
        "score": 42.3,
        "harness": "Claude Code",
        "version": "4.0",
        "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      },
      {
        "name": "DeepSWE",
        "score": 77,
        "harness": "Mini-SWE-V2",
        "version": "1.1",
        "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      },
      {
        "name": "ProgramBench",
        "score": 29.1,
        "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      },
      {
        "name": "NL2Repo",
        "score": 68.2,
        "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      },
      {
        "name": "AutomationBench",
        "score": 60.5,
        "version": "1.0.6",
        "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      },
      {
        "name": "Agents' Last Exam",
        "score": 35.4,
        "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      },
      {
        "name": "Apex Bench",
        "score": 72.1,
        "version": "1.1",
        "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      },
      {
        "name": "Chartography",
        "score": 83,
        "variant": "with tools",
        "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      },
      {
        "name": "BabyVision",
        "score": 92.5,
        "variant": "with tools",
        "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017"
      },
      {
        "name": "ZeroBench",
        "score": 51,
        "metric": "pass@5",
        "variant": "with tools",
        "dataset": "main",
        "source": "https://api-docs.deepseek.com/updates/"
      }
    ]
  },
  "usage": null
}