{
  "provider": "fireworks",
  "model_id": "qwen2p5-vl-32b-instruct",
  "display_name": "Qwen2.5-VL 32B Instruct",
  "status": "ga",
  "release_date": null,
  "deprecation_date": null,
  "retirement_date": null,
  "pricing": {
    "input_per_mtok": 0.9,
    "output_per_mtok": 0.9,
    "cached_input_per_mtok": null,
    "batch_discount_pct": null
  },
  "context_window_tokens": 128000,
  "max_output_tokens": null,
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "knowledge_cutoff": null,
  "sources": [
    {
      "url": "https://docs.fireworks.ai/serverless/pricing",
      "accessed_at": "2026-07-04T08:44:47Z",
      "fields": [
        "pricing.input_per_mtok",
        "pricing.output_per_mtok"
      ],
      "quote": "Prices below are per 1 million tokens in US dollars ... Other base models -- by size and architecture ... More than 16B parameters $0.90"
    },
    {
      "url": "https://fireworks.ai/models/fireworks/qwen2p5-vl-32b-instruct",
      "accessed_at": "2026-07-04T08:44:47Z",
      "fields": [
        "model_id",
        "context_window_tokens",
        "modalities"
      ],
      "quote": "model path:accounts/fireworks/models/qwen2p5-vl-32b-instruct ... Fireworks supports up to 128,000 tokens ... The model is supported on serverless deployment at $0.90 per million tokens ... Support image input Supported"
    }
  ],
  "verified_at": "2026-07-04T08:44:47Z",
  "notes": "Provider is Fireworks serving platform; upstream model family is Qwen. Generic >16B serverless token tier recorded.",
  "permalink": "/models/fireworks/qwen2p5-vl-32b-instruct.html"
}