{
  "_meta": {
    "source": "https://apipriceindex.com/api/deepinfra/qwen3.8-2.4t-a95b",
    "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": "2026-09-05T08:15:06.156Z"
  },
  "id": "deepinfra:qwen3.8-2.4t-a95b",
  "name": "Qwen3.8 2.4T A95B (DeepInfra)",
  "base_model": "qwen3.8-2.4t-a95b",
  "provider": {
    "id": "deepinfra",
    "name": "DeepInfra",
    "url": "https://deepinfra.com"
  },
  "category": "llm-chat",
  "capabilities": [
    "text",
    "function-calling"
  ],
  "context_window": 1048576,
  "max_output": 131072,
  "pricing": {
    "model_id": "deepinfra:qwen3.8-2.4t-a95b",
    "input": 2,
    "output": 6,
    "cached_input": 0.2,
    "source_url": "https://openrouter.ai/qwen/qwen3.8-2.4t-a95b",
    "verified_at": "2026-09-05T08:00:57Z",
    "sources": [
      {
        "name": "OpenRouter",
        "input": 2,
        "output": 6,
        "url": "https://openrouter.ai/qwen/qwen3.8-2.4t-a95b",
        "verified_at": "2026-09-05T08:00:57Z"
      },
      {
        "name": "LiteLLM",
        "input": 2,
        "output": 6,
        "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": 2,
        "output": 6,
        "url": "https://models.dev/",
        "verified_at": "2026-09-04T10:52:49Z"
      }
    ],
    "confidence": "corroborated",
    "delta_pct": 0
  },
  "price_history": [
    [
      "2026-09-03",
      2,
      6
    ]
  ],
  "latency": [],
  "license": {
    "license": "Apache 2.0",
    "tier": "permissive",
    "open_weights": true,
    "source_url": "https://huggingface.co/Qwen/Qwen3-32B/blob/main/LICENSE"
  },
  "cutoff": {
    "cutoff": "2025-09",
    "label": "September 2025",
    "source_url": "https://aiknowledgecutoff.com/"
  },
  "intelligence": null,
  "quality": null,
  "api": {
    "base_url": "https://openrouter.ai/api/v1",
    "model": "qwen/qwen3.8-2.4t-a95b",
    "via": "openrouter",
    "key_env": "OPENROUTER_API_KEY",
    "docs_url": "https://openrouter.ai/qwen/qwen3.8-2.4t-a95b",
    "or_provider": "DeepInfra"
  },
  "facts": [
    "Qwen3.8 2.4T A95B (DeepInfra) costs $2.00 input / $6.00 output per 1M tokens.",
    "Cached input cuts the input price by 90%.",
    "A chatbot workload (1000 in / 500 out tokens) costs $5.00 per 1,000 requests.",
    "Cross-checked: LiteLLM's public price index independently lists DeepInfra's qwen3.8-2.4t-a95b at $2.00/$6.00 per 1M — corroborating the price shown here (within 0%).",
    "Handles a 1,048,576-token context window, up to 131,072 output tokens.",
    "Open weights under Apache 2.0 — permissive licence.",
    "Training knowledge cutoff: September 2025.",
    "0% pricier than the cheapest qwen3.8-2.4t-a95b endpoint ($8.00 on Novita AI)."
  ]
}