{
  "_meta": {
    "source": "https://apipriceindex.com/api/relace/deepseek-v4-flash",
    "attribution": "apipriceindex.com",
    "license": "CC BY 4.0",
    "license_url": "https://creativecommons.org/licenses/by/4.0/",
    "note": "Free to reuse with attribution to apipriceindex.com.",
    "generated_at": "2026-09-05T08:15:05.939Z"
  },
  "id": "relace:deepseek-v4-flash",
  "name": "DeepSeek V4 Flash 0731 (Relace)",
  "base_model": "deepseek-v4-flash",
  "provider": {
    "id": "relace",
    "name": "Relace",
    "url": "https://relace.ai"
  },
  "category": "llm-chat",
  "capabilities": [
    "text",
    "function-calling"
  ],
  "context_window": 1310720,
  "max_output": 943718,
  "pricing": {
    "model_id": "relace:deepseek-v4-flash",
    "input": 0.065,
    "output": 0.18,
    "cached_input": 0.016,
    "source_url": "https://openrouter.ai/deepseek/deepseek-v4-flash-0731",
    "verified_at": "2026-09-05T08:00:57Z",
    "sources": [
      {
        "name": "OpenRouter",
        "input": 0.065,
        "output": 0.18,
        "url": "https://openrouter.ai/deepseek/deepseek-v4-flash-0731",
        "verified_at": "2026-09-05T08:00:57Z"
      },
      {
        "name": "LiteLLM",
        "input": 0.08,
        "output": 0.18,
        "url": "https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json",
        "verified_at": "2026-09-03T20:47:46Z"
      },
      {
        "name": "models.dev",
        "input": 0.065,
        "output": 0.18,
        "url": "https://models.dev/",
        "verified_at": "2026-09-04T10:52:49Z"
      }
    ],
    "confidence": "corroborated",
    "delta_pct": 0
  },
  "price_history": [
    [
      "2026-09-03",
      0.065,
      0.18
    ]
  ],
  "latency": [],
  "license": {
    "license": "MIT",
    "tier": "permissive",
    "open_weights": true,
    "source_url": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1"
  },
  "cutoff": {
    "cutoff": "2026-03",
    "label": "March 2026",
    "source_url": "https://aiknowledgecutoff.com/"
  },
  "intelligence": {
    "score": 51.8,
    "model_name": "DeepSeek V4 Flash 0731",
    "verified_at": "2026-09-04",
    "benchmark_label": "Artificial Analysis Intelligence Index",
    "source_url": "https://artificialanalysis.ai/"
  },
  "quality": {
    "elo": 1436,
    "arena_name": "DeepSeek-V4-Flash",
    "verified_at": "2026-09-04",
    "benchmark_label": "LMArena (Chatbot Arena)",
    "source_url": "https://lmarena.ai/leaderboard/text"
  },
  "api": {
    "base_url": "https://openrouter.ai/api/v1",
    "model": "deepseek/deepseek-v4-flash-0731",
    "via": "openrouter",
    "key_env": "OPENROUTER_API_KEY",
    "docs_url": "https://openrouter.ai/deepseek/deepseek-v4-flash-0731",
    "or_provider": "Relace"
  },
  "facts": [
    "DeepSeek V4 Flash 0731 (Relace) costs $0.07 input / $0.18 output per 1M tokens.",
    "Cached input cuts the input price by 75%.",
    "A chatbot workload (1000 in / 500 out tokens) costs $0.15 per 1,000 requests.",
    "Cross-checked against LiteLLM's public price index, which lists deepseek-v4-flash at $0.08/$0.18 per 1M (within 6% of this endpoint).",
    "Handles a 1,310,720-token context window, up to 943,718 output tokens.",
    "Open weights under MIT — permissive licence.",
    "Training knowledge cutoff: March 2026.",
    "Scores 1436 on the LMArena (Chatbot Arena) (human-preference leaderboard) for deepseek-v4-flash.",
    "Scores 51.8 on the Artificial Analysis Intelligence Index for deepseek-v4-flash.",
    "63% pricier than the cheapest deepseek-v4-flash endpoint ($0.15 on Baidu).",
    "Value: 1436 Elo at $0.24 blended = 5861 Elo points per dollar — ranking #12 of 321 priced & rated endpoints in the index.",
    "Intelligence value: 51.8 index at $0.24 blended = 211.4 index points per dollar — ranking #2 of 373 priced & AA-rated endpoints in the index."
  ]
}