{
  "_meta": {
    "source": "https://apipriceindex.com/api/digitalocean/minimax-m2.5",
    "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": "2026-09-05T08:15:06.132Z"
  },
  "id": "digitalocean:minimax-m2.5",
  "name": "MiniMax M2.5 (DigitalOcean)",
  "base_model": "minimax-m2.5",
  "provider": {
    "id": "digitalocean",
    "name": "DigitalOcean",
    "url": "https://www.digitalocean.com/products/gradient"
  },
  "category": "llm-chat",
  "capabilities": [
    "text",
    "function-calling"
  ],
  "context_window": 204800,
  "max_output": 58982,
  "pricing": {
    "model_id": "digitalocean:minimax-m2.5",
    "input": 0.3,
    "output": 1.2,
    "cached_input": 0.06,
    "source_url": "https://openrouter.ai/minimax/minimax-m2.5",
    "verified_at": "2026-09-05T08:00:57Z",
    "sources": [
      {
        "name": "OpenRouter",
        "input": 0.3,
        "output": 1.2,
        "url": "https://openrouter.ai/minimax/minimax-m2.5",
        "verified_at": "2026-09-05T08:00:57Z"
      },
      {
        "name": "LiteLLM",
        "input": 0.3,
        "output": 1.2,
        "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": 0.3,
        "output": 1.2,
        "url": "https://models.dev/",
        "verified_at": "2026-09-04T10:52:49Z"
      }
    ],
    "confidence": "corroborated",
    "delta_pct": 0
  },
  "price_history": [
    [
      "2026-09-03",
      0.3,
      1.2
    ]
  ],
  "latency": [],
  "license": {
    "license": "MiniMax Model License",
    "tier": "conditional",
    "open_weights": true,
    "source_url": "https://huggingface.co/MiniMaxAI"
  },
  "cutoff": {
    "cutoff": "2026-01",
    "label": "January 2026",
    "source_url": "https://aiknowledgecutoff.com/"
  },
  "intelligence": {
    "score": 34.5,
    "model_name": "MiniMax M2.5",
    "verified_at": "2026-09-04",
    "benchmark_label": "Artificial Analysis Intelligence Index",
    "source_url": "https://artificialanalysis.ai/"
  },
  "quality": {
    "elo": 1391,
    "arena_name": "MiniMax M2.5",
    "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": "minimax/minimax-m2.5",
    "via": "openrouter",
    "key_env": "OPENROUTER_API_KEY",
    "docs_url": "https://openrouter.ai/minimax/minimax-m2.5",
    "or_provider": "DigitalOcean"
  },
  "facts": [
    "MiniMax M2.5 (DigitalOcean) costs $0.30 input / $1.20 output per 1M tokens.",
    "Cached input cuts the input price by 80%.",
    "A chatbot workload (1000 in / 500 out tokens) costs $0.90 per 1,000 requests.",
    "Cross-checked against LiteLLM's public price index, which lists minimax-m2.5 at $0.30/$1.20 per 1M (within 0% of this endpoint).",
    "Handles a 204,800-token context window, up to 58,982 output tokens.",
    "Open weights under MiniMax Model License — conditional licence.",
    "Training knowledge cutoff: January 2026.",
    "Scores 1391 on the LMArena (Chatbot Arena) (human-preference leaderboard) for minimax-m2.5.",
    "Scores 34.5 on the Artificial Analysis Intelligence Index for minimax-m2.5.",
    "23% pricier than the cheapest minimax-m2.5 endpoint ($1.22 on Venice).",
    "Value: 1391 Elo at $1.50 blended = 927 Elo points per dollar — ranking #146 of 321 priced & rated endpoints in the index.",
    "Intelligence value: 34.5 index at $1.50 blended = 23.0 index points per dollar — ranking #134 of 373 priced & AA-rated endpoints in the index."
  ]
}