{
  "_meta": {
    "source": "https://apipriceindex.com/api/mistral/mistral-large",
    "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": "2026-09-05T08:15:05.893Z"
  },
  "id": "mistral:mistral-large",
  "name": "Mistral Large 3 (Mistral)",
  "base_model": "mistral-large",
  "provider": {
    "id": "mistral",
    "name": "Mistral AI",
    "url": "https://mistral.ai"
  },
  "category": "llm-chat",
  "capabilities": [
    "text",
    "function-calling"
  ],
  "context_window": 131072,
  "max_output": 32768,
  "pricing": {
    "model_id": "mistral:mistral-large",
    "input": 0.5,
    "output": 1.5,
    "cached_input": null,
    "source_url": "https://openrouter.ai/mistralai/mistral-large-2512",
    "verified_at": "2026-09-03",
    "sources": [
      {
        "name": "OpenRouter",
        "input": 0.5,
        "output": 1.5,
        "url": "https://openrouter.ai/mistralai/mistral-large-2512",
        "verified_at": "2026-09-03"
      },
      {
        "name": "LiteLLM",
        "input": 4,
        "output": 12,
        "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": 0.5,
        "output": 1.5,
        "url": "https://models.dev/",
        "verified_at": "2026-09-04T10:52:49Z"
      }
    ],
    "confidence": "corroborated",
    "delta_pct": 0
  },
  "price_history": [
    [
      "2026-09-03",
      0.5,
      1.5
    ]
  ],
  "latency": [
    {
      "model_id": "mistral:mistral-large",
      "region": "eu-paris",
      "ttft_ms": {
        "p50": 360.7,
        "p95": 375.6
      },
      "total_ms": {
        "p50": 2636.2,
        "p95": 2789.8
      },
      "tokens_per_s": 70.3,
      "samples": 5,
      "error_rate": 0,
      "token_source": "usage",
      "measured_at": "2026-09-04T18:49:24Z"
    }
  ],
  "license": {
    "license": "Mistral Research License",
    "tier": "conditional",
    "open_weights": true,
    "source_url": "https://mistral.ai/licenses/MRL-0.1.md"
  },
  "cutoff": {
    "cutoff": "2024-07",
    "label": "July 2024",
    "source_url": "https://docs.mistral.ai/getting-started/models/models_overview/"
  },
  "intelligence": null,
  "quality": {
    "elo": 1414,
    "arena_name": "Mistral Large 3",
    "verified_at": "2026-09-04",
    "benchmark_label": "LMArena (Chatbot Arena)",
    "source_url": "https://lmarena.ai/leaderboard/text"
  },
  "api": {
    "base_url": "https://api.mistral.ai/v1",
    "model": "mistral-large-2512",
    "via": "first-party",
    "key_env": "MISTRAL_API_KEY",
    "docs_url": null
  },
  "facts": [
    "Mistral Large 3 (Mistral) costs $0.50 input / $1.50 output per 1M tokens.",
    "A chatbot workload (1000 in / 500 out tokens) costs $1.25 per 1,000 requests.",
    "Handles a 131,072-token context window, up to 32,768 output tokens.",
    "Open weights under Mistral Research License — conditional licence.",
    "Training knowledge cutoff: July 2024.",
    "Scores 1414 on the LMArena (Chatbot Arena) (human-preference leaderboard) for mistral-large.",
    "From eu-paris, p50 time-to-first-token is 361 ms (5 samples).",
    "Value: 1414 Elo at $2.00 blended = 707 Elo points per dollar — ranking #168 of 321 priced & rated endpoints in the index.",
    "Throughput: 70 tokens/s measured from eu-paris at $2.00 blended = 35.1 tokens/s per dollar — ranking #9 of 11 priced & speed-tested endpoints in the index."
  ]
}