{
  "access_checked_at": "2026-10-28T16:44:42Z",
  "access_evidence": [
    {
      "claim_type": "official_access_public",
      "official_model_id": "qwen-flash",
      "scope": "Exact hosted API model on Alibaba Cloud Model Studio under ordinary pay-as-you-go account requirements (International scope).",
      "title": "qwen-flash official model documentation",
      "url": "https://www.alibabacloud.com/help/en/model-studio/qwen-flash"
    }
  ],
  "access_status": "public",
  "accessed_at": "2026-10-28T16:44:42Z",
  "binding_evidence": [
    {
      "claim_type": "official_identity_binding",
      "official_model_id": "qwen-flash",
      "reason": "Exact documented API model ID; no entitlement inherited from a billing target.",
      "title": "qwen-flash official identity documentation",
      "url": "https://www.alibabacloud.com/help/en/model-studio/qwen-flash"
    }
  ],
  "binding_status": "approved",
  "context_window_tokens": 1000000,
  "display_name": "Qwen Flash",
  "effective_from": null,
  "last_verified_at": "2026-10-28T16:44:42Z",
  "model_family": "Qwen",
  "model_id": "qwen-flash",
  "notes": "Official API model ID qwen-flash, currently equivalent to snapshot qwen-flash-2025-07-28. Text-only; 1,000,000-token context window, maximum input 997,952 tokens and maximum output 32,768 tokens. Pricing is tiered by input tokens per request: up to 256K, and 256K to 1M; the tier applies to every token in the request. The model page lists batch-file rates for Singapore but also marks batch inference as unsupported there, so no batch price is represented. Prices are USD list prices for the International (Singapore) scope; the official model page states that it shows original prices excluding limited-time promotions.",
  "official_source_url": "https://www.alibabacloud.com/help/en/model-studio/qwen-flash",
  "official_source_urls": [
    "https://www.alibabacloud.com/help/en/model-studio/qwen-flash",
    "https://www.alibabacloud.com/help/en/model-studio/model-pricing"
  ],
  "price_records": [
    {
      "billing_note": "Standard list pricing for requests with 256,000 or fewer input tokens, International (Singapore) deployment scope; the US scope lists the same rates, while the Global and Chinese mainland scopes publish lower rates. Cached input is the implicit (automatic) cache-hit rate. Explicit caching is a separate opt-in mode with a 5-minute TTL: creation $0.063 and reads $0.005 per 1M tokens.",
      "calculation_default": true,
      "charges": [
        {
          "amount": "0.05",
          "component": "input",
          "id": "price:alibaba-qwen/qwen-flash:standard:short:current:input:text:per_1m_tokens",
          "modality": "text",
          "unit": "per_1m_tokens"
        },
        {
          "amount": "0.01",
          "component": "cached_input",
          "id": "price:alibaba-qwen/qwen-flash:standard:short:current:cached_input:text:per_1m_tokens",
          "modality": "text",
          "unit": "per_1m_tokens"
        },
        {
          "amount": "0.4",
          "component": "output",
          "id": "price:alibaba-qwen/qwen-flash:standard:short:current:output:text:per_1m_tokens",
          "modality": "text",
          "unit": "per_1m_tokens"
        }
      ],
      "checked_at": "2026-10-28T16:44:42Z",
      "context_class": "short",
      "currency": "USD",
      "effective_from": null,
      "effective_until": null,
      "id": "price:alibaba-qwen/qwen-flash:standard:short:current",
      "pricing_status": "current",
      "processing_mode": "standard",
      "prompt_token_threshold": 256000,
      "region_policy": {
        "availability": {
          "default": "available",
          "rules": []
        },
        "data_residencies": [
          "regional"
        ],
        "endpoint_geographies": [
          "ap-southeast-1"
        ],
        "price_adjustments": [],
        "pricing_geography": "region_specific"
      },
      "source_refs": [
        "https://www.alibabacloud.com/help/en/model-studio/qwen-flash",
        "https://www.alibabacloud.com/help/en/model-studio/model-pricing"
      ],
      "tier_selection": {
        "cached_prompt_tokens_included": true,
        "comparison": "less_than_or_equal",
        "token_basis": "input_tokens",
        "whole_request_pricing": true
      },
      "verification_status": "verified",
      "verified_at": "2026-10-28T16:44:42Z"
    },
    {
      "billing_note": "Standard list pricing for requests with more than 256,000 input tokens (up to 1M); the tier applies to the whole request. International (Singapore) deployment scope; the US scope lists the same rates, while the Global and Chinese mainland scopes publish lower rates. Cached input is the implicit (automatic) cache-hit rate. Explicit caching is a separate opt-in mode with a 5-minute TTL: creation $0.313 and reads $0.025 per 1M tokens.",
      "calculation_default": false,
      "charges": [
        {
          "amount": "0.25",
          "component": "input",
          "id": "price:alibaba-qwen/qwen-flash:standard:long:current:input:text:per_1m_tokens",
          "modality": "text",
          "unit": "per_1m_tokens"
        },
        {
          "amount": "0.05",
          "component": "cached_input",
          "id": "price:alibaba-qwen/qwen-flash:standard:long:current:cached_input:text:per_1m_tokens",
          "modality": "text",
          "unit": "per_1m_tokens"
        },
        {
          "amount": "2",
          "component": "output",
          "id": "price:alibaba-qwen/qwen-flash:standard:long:current:output:text:per_1m_tokens",
          "modality": "text",
          "unit": "per_1m_tokens"
        }
      ],
      "checked_at": "2026-10-28T16:44:42Z",
      "context_class": "long",
      "currency": "USD",
      "effective_from": null,
      "effective_until": null,
      "id": "price:alibaba-qwen/qwen-flash:standard:long:current",
      "pricing_status": "current",
      "processing_mode": "standard",
      "prompt_token_threshold": 256000,
      "region_policy": {
        "availability": {
          "default": "available",
          "rules": []
        },
        "data_residencies": [
          "regional"
        ],
        "endpoint_geographies": [
          "ap-southeast-1"
        ],
        "price_adjustments": [],
        "pricing_geography": "region_specific"
      },
      "source_refs": [
        "https://www.alibabacloud.com/help/en/model-studio/qwen-flash",
        "https://www.alibabacloud.com/help/en/model-studio/model-pricing"
      ],
      "tier_selection": {
        "cached_prompt_tokens_included": true,
        "comparison": "greater_than",
        "token_basis": "input_tokens",
        "whole_request_pricing": true
      },
      "verification_status": "verified",
      "verified_at": "2026-10-28T16:44:42Z"
    }
  ],
  "pricing": {
    "batch_input": null,
    "batch_output": null,
    "cache_write": null,
    "cache_write_1h": null,
    "cached_input": 0.01,
    "currency": "USD",
    "input": 0.05,
    "output": 0.4,
    "unit": "1M tokens"
  },
  "project_context_window": true,
  "provider_id": "alibaba-qwen",
  "release_evidence": null,
  "release_stage": "stable",
  "released_at": null,
  "status": "active"
}