{
  "_meta": {
    "source": "https://apipriceindex.com/api/mistral/mistral-small",
    "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": "2026-09-05T08:15:05.891Z"
  },
  "id": "mistral:mistral-small",
  "name": "Mistral Small (Mistral)",
  "base_model": "mistral-small",
  "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-small",
    "input": 0.15,
    "output": 0.6,
    "cached_input": null,
    "source_url": "https://openrouter.ai/mistralai/mistral-small-2603",
    "verified_at": "2026-09-03",
    "sources": [
      {
        "name": "OpenRouter",
        "input": 0.15,
        "output": 0.6,
        "url": "https://openrouter.ai/mistralai/mistral-small-2603",
        "verified_at": "2026-09-03"
      },
      {
        "name": "LiteLLM",
        "input": 0.1,
        "output": 0.3,
        "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": 0.1,
        "output": 0.3,
        "url": "https://models.dev/",
        "verified_at": "2026-09-04T10:52:49Z"
      }
    ],
    "confidence": "diverges",
    "delta_pct": 46.7
  },
  "price_history": [
    [
      "2026-09-03",
      0.15,
      0.6
    ]
  ],
  "latency": [
    {
      "model_id": "mistral:mistral-small",
      "region": "eu-paris",
      "ttft_ms": {
        "p50": 270.5,
        "p95": 320.3
      },
      "total_ms": {
        "p50": 1575.7,
        "p95": 1630.3
      },
      "tokens_per_s": 142.1,
      "samples": 5,
      "error_rate": 0,
      "token_source": "usage",
      "measured_at": "2026-09-04T18:46:04Z"
    }
  ],
  "license": {
    "license": "Apache 2.0",
    "tier": "permissive",
    "open_weights": true,
    "source_url": "https://huggingface.co/mistralai"
  },
  "cutoff": {
    "cutoff": "2025-06",
    "label": "June 2025",
    "source_url": "https://docs.mistral.ai/getting-started/models/models_overview/"
  },
  "intelligence": null,
  "quality": null,
  "api": {
    "base_url": "https://api.mistral.ai/v1",
    "model": "mistral-small-2603",
    "via": "first-party",
    "key_env": "MISTRAL_API_KEY",
    "docs_url": null
  },
  "facts": [
    "Mistral Small (Mistral) costs $0.15 input / $0.60 output per 1M tokens.",
    "A chatbot workload (1000 in / 500 out tokens) costs $0.45 per 1,000 requests.",
    "Handles a 131,072-token context window, up to 32,768 output tokens.",
    "Open weights under Apache 2.0 — permissive licence.",
    "Training knowledge cutoff: June 2025.",
    "From eu-paris, p50 time-to-first-token is 270 ms (5 samples).",
    "Cheapest of 2 providers serving mistral-small: $0.75 blended per 1M tokens, vs $0.94 for the next cheapest.",
    "Throughput: 142 tokens/s measured from eu-paris at $0.75 blended = 189.5 tokens/s per dollar — ranking #6 of 11 priced & speed-tested endpoints in the index."
  ]
}