{
  "provider": "google",
  "model_id": "gemini-2.5-flash",
  "display_name": "Gemini 2.5 Flash",
  "status": "ga",
  "release_date": null,
  "deprecation_date": null,
  "retirement_date": null,
  "pricing": {
    "input_per_mtok": 0.3,
    "output_per_mtok": 2.5,
    "cached_input_per_mtok": 0.03,
    "batch_discount_pct": null
  },
  "context_window_tokens": 1048576,
  "max_output_tokens": null,
  "modalities": {
    "input": [
      "text",
      "image",
      "video"
    ],
    "output": [
      "text"
    ]
  },
  "knowledge_cutoff": null,
  "sources": [
    {
      "url": "https://ai.google.dev/gemini-api/docs/pricing",
      "accessed_at": "2026-07-04T05:55:32Z",
      "fields": [
        "pricing.input_per_mtok",
        "pricing.output_per_mtok",
        "pricing.cached_input_per_mtok",
        "modalities"
      ],
      "quote": "Gemini 2.5 Flash `gemini-2.5-flash` Our first hybrid reasoning model which supports a 1M token context window ... Input price Free of charge $0.30 (text / image / video) $1.00 (audio) Output price (including thinking tokens) Free of charge $2.50 Context caching price Not available $0.03 (text / image / video)"
    },
    {
      "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash",
      "accessed_at": "2026-07-04T07:37:12Z",
      "fields": [
        "context_window_tokens"
      ],
      "quote": "Gemini 2.5 Flash ... Model code gemini-2.5-flash ... Token limits ... Input token limit 1,048,576 Output token limit 65,536"
    }
  ],
  "verified_at": "2026-07-04T07:37:12Z",
  "notes": "Gemini pricing may vary by modality and prompt length; this entry records the cited standard text or text/image/video tier.",
  "permalink": "/models/google/gemini-2_5-flash.html"
}