{
  "_meta": {
    "source": "https://apipriceindex.com/api/deepinfra/gemma-4-31b",
    "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": "2026-09-05T08:15:06.049Z"
  },
  "id": "deepinfra:gemma-4-31b",
  "name": "Gemma 4 31B (DeepInfra)",
  "base_model": "gemma-4-31b",
  "provider": {
    "id": "deepinfra",
    "name": "DeepInfra",
    "url": "https://deepinfra.com"
  },
  "category": "llm-chat",
  "capabilities": [
    "text",
    "vision"
  ],
  "context_window": 262144,
  "max_output": 16384,
  "pricing": {
    "model_id": "deepinfra:gemma-4-31b",
    "input": 0.27,
    "output": 0.76,
    "cached_input": null,
    "source_url": "https://openrouter.ai/google/gemma-4-31b-it",
    "verified_at": "2026-09-03T20:42:42Z",
    "sources": [
      {
        "name": "OpenRouter",
        "input": 0.27,
        "output": 0.76,
        "url": "https://openrouter.ai/google/gemma-4-31b-it",
        "verified_at": "2026-09-03T20:42:42Z"
      },
      {
        "name": "LiteLLM",
        "input": 0.13,
        "output": 0.38,
        "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": 0.13,
        "output": 0.38,
        "url": "https://models.dev/",
        "verified_at": "2026-09-04T10:52:49Z"
      }
    ],
    "confidence": "tier-mismatch",
    "delta_pct": 50.5
  },
  "price_history": [
    [
      "2026-09-03",
      0.27,
      0.76
    ]
  ],
  "latency": [],
  "license": {
    "license": "Gemma Terms of Use",
    "tier": "conditional",
    "open_weights": true,
    "source_url": "https://ai.google.dev/gemma/terms"
  },
  "cutoff": {
    "cutoff": "2025-01",
    "label": "January 2025",
    "source_url": "https://ai.google.dev/gemma/docs"
  },
  "intelligence": {
    "score": 29.7,
    "model_name": "Gemma 4 31B",
    "verified_at": "2026-09-04",
    "benchmark_label": "Artificial Analysis Intelligence Index",
    "source_url": "https://artificialanalysis.ai/"
  },
  "quality": {
    "elo": 1451,
    "arena_name": "Gemma 4 31B",
    "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": "google/gemma-4-31b-it",
    "via": "openrouter",
    "key_env": "OPENROUTER_API_KEY",
    "docs_url": "https://openrouter.ai/google/gemma-4-31b-it",
    "or_provider": "DeepInfra"
  },
  "facts": [
    "Gemma 4 31B (DeepInfra) costs $0.27 input / $0.76 output per 1M tokens.",
    "A chatbot workload (1000 in / 500 out tokens) costs $0.65 per 1,000 requests.",
    "Handles a 262,144-token context window, up to 16,384 output tokens.",
    "Open weights under Gemma Terms of Use — conditional licence.",
    "Training knowledge cutoff: January 2025.",
    "Scores 1451 on the LMArena (Chatbot Arena) (human-preference leaderboard) for gemma-4-31b.",
    "Scores 29.7 on the Artificial Analysis Intelligence Index for gemma-4-31b.",
    "134% pricier than the cheapest gemma-4-31b endpoint ($0.44 on CoreWeave).",
    "Value: 1451 Elo at $1.03 blended = 1409 Elo points per dollar — ranking #98 of 321 priced & rated endpoints in the index.",
    "Intelligence value: 29.7 index at $1.03 blended = 28.8 index points per dollar — ranking #116 of 373 priced & AA-rated endpoints in the index."
  ]
}