{
  "schemaVersion": 1,
  "id": "alibaba-qwen-provider-pricing-2026",
  "lastVerifiedAt": null,
  "reviewedApiLastVerifiedAt": "2026-11-09T20:42:22.341Z",
  "allCurrent": false,
  "claims": {
    "models": [
      {
        "id": "alibaba-qwen3.6-flash",
        "name": "Qwen3.6-Flash",
        "provider": "alibaba",
        "endpoint": "qwen3.6-flash",
        "host": "Alibaba Model Studio · Singapore / International",
        "pricing": {
          "inputPerM": 0.25,
          "cachedInputPerM": 0.025,
          "cacheWritePerM": 0.3125,
          "outputPerM": 1.5,
          "longContext": {
            "thresholdInputTokens": 256000,
            "thresholdInclusive": false,
            "inputPerM": 1,
            "cachedInputPerM": 0.1,
            "cacheWritePerM": 1.25,
            "outputPerM": 4
          }
        },
        "condition": "Standard rate through 256K input tokens; higher request tier above that."
      },
      {
        "id": "alibaba-qwen3.7-plus",
        "name": "Qwen3.7-Plus",
        "provider": "alibaba",
        "endpoint": "qwen3.7-plus",
        "host": "Alibaba Model Studio · Singapore / International",
        "pricing": {
          "inputPerM": 0.32,
          "cachedInputPerM": 0.032,
          "cacheWritePerM": 0.4,
          "outputPerM": 1.28,
          "longContext": {
            "thresholdInputTokens": 256000,
            "thresholdInclusive": false,
            "inputPerM": 0.96,
            "cachedInputPerM": 0.096,
            "cacheWritePerM": 1.2,
            "outputPerM": 3.84
          }
        },
        "condition": "Limited-time 20% discount on the alias; no public end date. Standard tier through 256K input tokens."
      },
      {
        "id": "alibaba-qwen3.7-max",
        "name": "Qwen3.7-Max",
        "provider": "alibaba",
        "endpoint": "qwen3.7-max",
        "host": "Alibaba Model Studio · Singapore / International",
        "pricing": {
          "inputPerM": 2.5,
          "cachedInputPerM": 0.25,
          "cacheWritePerM": 3.125,
          "outputPerM": 7.5
        },
        "condition": "Standard international rate through the 1M-input-token tier; no promotional discount assumed."
      },
      {
        "id": "cerebras-qwen3.8-27b",
        "name": "Qwen3.8 27B",
        "provider": "cerebras",
        "endpoint": "qwen-3.8-27b",
        "host": "Cerebras · Developer",
        "pricing": {
          "inputPerM": 0.99,
          "outputPerM": 1.49
        },
        "condition": "Developer token billing; trial and paid limits differ."
      }
    ],
    "alibabaBilling": "Alibaba rates here are USD per 1M tokens in the Singapore / International scope, not China-region prices. Calls are pay-as-you-go by default. The total input-token count selects the request tier, and all tokens in that request use the corresponding tier rate. Qwen3.7-Plus applies the explicitly published 20% alias promotion; its dated snapshot does not automatically inherit that promotion.",
    "cacheBoundary": "Cache-hit input is separate from standard input. Alibaba documents typical explicit-cache creation at 125% and explicit hits at 10% of standard input; implicit hits are typically 20%. Modes are mutually exclusive, hits are not guaranteed, and model-specific cache billing governs. Do not stack cache and batch discounts or interpret one cache mode as the other.",
    "quotaBoundary": "The current Singapore / International table lists no free quota for Qwen3.6-Flash. Qwen3.7-Plus and Qwen3.7-Max list a selected-model activation quota of 1 million tokens, valid for 90 days from activation, model release or application approval, whichever is later. This is not a recurring free production allowance and does not establish Qwen Studio plan entitlement.",
    "cerebrasAccess": "The exact Cerebras endpoint is qwen-3.8-27b. Free Trial has 65,536 context tokens and 32,768 maximum output tokens; paid tiers and trial customers have 131,072 context tokens and 40,960 maximum output tokens. Free Trial is limited to 5 requests/minute and 1M tokens/day; Developer lists 300 requests/minute, 150K uncached tokens/minute, temporarily 750K total tokens/minute, and no daily token limit. It accepts text and PNG/JPEG image input and produces text. Free Trial permits 2 images per request, while Developer and Enterprise Shared Inference permit 10; maximum request payload is 10 MiB.",
    "cerebrasBilling": "Cerebras states that adding a valid payment method can grant a one-time promotional credit of USD 5, expiring after 30 days. There is no automatic paid enrollment; API and Playground access pause when the credit expires or is exhausted unless PayGo credits are separately purchased. Development/evaluation tier access is not a production entitlement; enterprise capacity and terms require agreement.",
    "cerebrasSpeedTokensPerSecond": 1850,
    "flashBoundary": "The current Alibaba Model Studio catalog and international rate card list qwen3.8-flash. The older QwenCloud announcement is not current evidence that this route is still coming soon, nor proof that its historical price is the same product. The shared catalog row is excluded from this page’s current-price subset until its exact first-party rate and availability pass the existing reconciliation gate.",
    "studio": {
      "price": null,
      "quota": null,
      "modelEntitlements": null,
      "boundary": "Qwen Studio chat access is a different product from Alibaba Model Studio API billing. The public Qwen product and chat URLs returned app shells, without meaningful plan-price, quota or model-entitlement evidence. A paid plan, fixed free allowance or zero-dollar production API cannot be verified from these responses."
    },
    "unresolved": [
      {
        "id": "alibaba-qwen3.8-flash",
        "kind": "canonical-route-reconciliation-required",
        "label": "Qwen3.8-Flash first-party route",
        "reason": "The current Model Studio listing conflicts with the shared catalog’s historical QwenCloud coming-soon status and input rate. No price or access clock was advanced; the existing two-source price-change gate remains required."
      },
      {
        "id": "qwen-studio-product",
        "kind": "source-content-unusable",
        "label": "Qwen Studio product plans",
        "url": "https://qwen.ai/qwenchat",
        "reason": "HTTP 200 returned only an app shell. Subscription price, limits and model access remain unknown."
      },
      {
        "id": "qwen-studio-chat",
        "kind": "source-content-unusable",
        "label": "Qwen chat plan entitlement",
        "url": "https://chat.qwen.ai/",
        "reason": "HTTP 200 returned no meaningful server-rendered plan content. No free-plan or model entitlement is inferred."
      }
    ]
  },
  "evidence": {
    "models": [
      {
        "id": "alibaba-qwen3.6-flash",
        "priceLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "modelAccessLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "limitsLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "billingLastVerifiedAt": "2026-11-09T20:42:22.341Z"
      },
      {
        "id": "alibaba-qwen3.7-plus",
        "priceLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "modelAccessLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "limitsLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "billingLastVerifiedAt": "2026-11-09T20:42:22.341Z"
      },
      {
        "id": "alibaba-qwen3.7-max",
        "priceLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "modelAccessLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "limitsLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "billingLastVerifiedAt": "2026-11-09T20:42:22.341Z"
      },
      {
        "id": "cerebras-qwen3.8-27b",
        "priceLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "modelAccessLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "limitsLastVerifiedAt": "2026-11-09T20:42:22.341Z",
        "billingLastVerifiedAt": "2026-11-09T20:42:22.341Z"
      }
    ],
    "studio": {
      "priceLastVerifiedAt": null,
      "modelAccessLastVerifiedAt": null,
      "limitsLastVerifiedAt": null,
      "billingLastVerifiedAt": null
    }
  },
  "sources": [
    {
      "label": "catalog",
      "url": "https://www.alibabacloud.com/help/en/model-studio/models",
      "state": "reviewed semantic source"
    },
    {
      "label": "pricing",
      "url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
      "state": "reviewed semantic source"
    },
    {
      "label": "cache",
      "url": "https://www.alibabacloud.com/help/en/model-studio/context-cache",
      "state": "reviewed semantic source"
    },
    {
      "label": "cerebrasModel",
      "url": "https://inference-docs.cerebras.ai/models/qwen-3.8-27b.md",
      "state": "reviewed semantic source"
    },
    {
      "label": "cerebrasPricing",
      "url": "https://www.cerebras.ai/pricing",
      "state": "reviewed semantic source"
    },
    {
      "label": "Qwen Studio product plans",
      "url": "https://qwen.ai/qwenchat",
      "state": "unresolved — app shell is not verification"
    },
    {
      "label": "Qwen chat plan entitlement",
      "url": "https://chat.qwen.ai/",
      "state": "unresolved — app shell is not verification"
    }
  ],
  "reviewedContract": {
    "reviewedAt": "2026-10-21T05:57:51.137Z",
    "evidenceDirectory": "/opt/aipricing/data/control/evidence/6bd0b773-4829-41a1-bff5-6c3e11fca1fa",
    "pageSha256": "1db2554c002263ad94eb0b4db46c7ab2eeddf85ea7369c7753ede43cec7fe97e",
    "payloadSha256": "f3d853437cda395bb8b0a22ffc949c17d70a4ccab91ba1001063ff5601cdcc29",
    "projections": {
      "https://www.alibabacloud.com/help/en/model-studio/models": {
        "listed": [
          "qwen3.7-plus",
          "qwen3.8-flash"
        ],
        "flashEndpoint": "https://modelstudio.console.alibabacloud.com/ap-southeast-1/model/market/detail/qwen3.8-flash"
      },
      "https://www.alibabacloud.com/help/en/model-studio/model-pricing": {
        "models": {
          "qwen3.7-max": [
            "qwen3.7-max Currently equivalent to qwen3.7-max-2026-05-20 context caching discount International Non-Thinking and Thinking modes 0<Token≤1M $2.5 $7.5 1 million tokens"
          ],
          "qwen3.7-plus": [
            "qwen3.7-plus Currently equivalent to qwen3.7-plus-2026-05-26 context caching discount International 0<Token≤256K List price $0.4 (Limited-time 20% off) List price $1.6 (Limited-time 20% off) List price $1.6 (Limited-time 20% off) 1 million tokens",
            "256K<Token≤1M List price $1.2 (Limited-time 20% off) List price $4.8 (Limited-time 20% off) List price $4.8 (Limited-time 20% off)"
          ],
          "qwen3.6-flash": [
            "qwen3.6-flash Currently equivalent to qwen3.6-flash-2026-04-16 50% batch inference discount context caching discount International 0<Token≤256K $0.25 $1.5 No free quota",
            "256K<Token≤1M $1 $4"
          ],
          "qwen3.8-flash": [
            "qwen3.8-flash context caching discount International 0<Token≤1M $0.15 $0.47 1 million tokens"
          ]
        },
        "billing": "Model API calls are billed on a pay-as-you-go basis by default. Note This document only lists standard prices . For the latest promotions, visit the Model Studio console . Note Some models support context caching (explicit cache and implicit cache). Cache-hit input tokens and the tokens used to create an explicit cache are billed at unit prices different from the standard input price (for example, explicit cache creation is billed at 125% of the standard input price, and cache hits at 10%). The input prices in the tables below do not include cache prices. For cache billing rules, discount rates, and supported models, see Context Cache . Tiered pricing rules Some Model Studio models use tiered pricing. The unit price is determined by the total number of input tokens in a single request. All tokens in the request are billed at the unit price of the corresponding tier. In the pricing tiers, K means 1,000 and M means 1,000,000. For example, 128K equals 128,000 tokens, 256K equals 256,000 tokens, and 1M equals 1,000,000 tokens. For example, a model has two pricing tiers: 0 < tokens ≤ 32K and 32K < tokens ≤ 128K. If a request contains 100K input tokens, it falls into the second tier (32K < 100K ≤ 128K), and all tokens are billed at the unit price of the second tier. ",
        "quota": "The following models offer a free quota only in Singapore. No free quota is available in other regions. Singapore Model ID Deployment scope Mode Input tokens per request Input price (per 1 million tokens) Output price (per 1 million tokens) Chain of thought + answer Free quota (Note) Valid for 90 days from the date of Model Studio activation, model release, or application approval, whichever is later"
      },
      "https://www.alibabacloud.com/help/en/model-studio/context-cache": {
        "terms": "Inference requests for large models often contain overlapping input, such as in a multi-turn conversation or a series of questions about the same book. Context Cache reduces redundant computation by caching the common prefix of these requests. This improves response speed and lowers usage costs without affecting response quality. To support different scenarios, context cache offers two modes. Choose a mode based on your requirements for convenience, determinism, and cost: Explicit cache : A mode that you enable manually. You create a cache for specific content to ensure a deterministic hit within its 5-minute validity period. Tokens used to create the cache are typically billed at 125% of the standard input token price, while subsequent cache hits are typically billed at only 10% of that price. For specific pricing, see Billing . Implicit cache : This automatic mode requires no extra configuration and cannot be disabled, ideal for scenarios that prioritize convenience. The system automatically identifies and caches the common prefix of requests, but the hit probability is not guaranteed . The portion of the input served from the cache is typically billed at 20% of the standard input token price. For specific pricing, see Billing . Item Explicit cache Implicit cache Impact on response quality No No Billing for cache creation tokens Typically 125% of the standard input token price 100% of the standard input token price Billing for cached input tokens Typically 10% of the standard input token price (see Billing ) Typically 20% of the standard input token price (see Billing ) Minimum tokens for caching 1024 1024 Cache validity period 5 minutes (resets on hit) Indeterminate. The system periodically clears old, unused cache data. Although the minimum token count is the same for both modes, the meaning differs: explicit cache is actively created and managed by the user; implicit cache is automatically created and managed by the system. Reaching 1,024 tokens only means the request meets the technical conditions for a cache hit, but does not guarantee an actual hit. Note Explicit cache and implicit cache are mutually exclusive. Note Provisioned Throughput Unit (PTU) deployments also support context cache. When a cache hit occurs, the system calculates PTU usage with a cache discount factor. For more information, see Long inputs and caching for PTU . Note Examples below use Chat Completions, DashScope, and Anthropic-compatible APIs. Responses API has separate Session cache settings. Explicit cache Unlike an implicit cache, an explicit cache requires explicit creation and incurs overhead, but delivers a higher cache hit ratio and lower access latency. How it works Add a &quot;cache_control&quot;: {&quot;type&quot;: &quot;ephemeral&quot;} marker to the messages array. The system then searches backward from each cache_control marker and examines up to 20 preceding content blocks to find a cache hit. A single request supports up to four cache markers. Cache miss If a cache miss occurs, the system creates a new cache block from the content between the start of the messages array and the cache_control marker. The new cache block has a validity period of 5 minutes. The system creates the cache after the model generates a response. Wait for the creation request to complete before trying to hit that cache. A cache block contains at least 1,024 tokens. Cache hit If a cache hit occurs, the system selects the longest matching prefix and resets the validity period of the corresponding cache block to 5 minutes. The following example demonstrates how this works: Send the first request : Send a system message containing text A (more than 1,024 tokens), and add a cache marker: [{&quot;role&quot;: &quot;system&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: A, &quot;cache_control&quot;: {&quot;type&quot;: &quot;ephemeral&quot;}}]}] The system creates the first cache block, calling it cache block A. 2. Send the second request: Send a request with the following structure: [ {&quot;role&quot;: &quot;system&quot;, &quot;content&quot;: A}, <Other messages> {&quot;role&quot;: &quot;user&quot;,&quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: B, &quot;cache_control&quot;: {&quot;type&quot;: &quot;ephemeral&quot;}}]} ] If there are 20 or fewer &quot;Other messages,&quot; the request hits cache block A, resetting its validity period to 5 minutes. The system also creates a new cache block based on A, the other messages, and B. If there are more than 20 &quot;Other messages,&quot; the request misses cache block A. The system still creates a new cache block based on the full context (A, the other messages, and B). ",
        "explicitBilling": "Billing Explicit cache only affects how input tokens are billed. The rules are as follows: Cache creation : Content used to create a new cache is billed at 125% of the standard input token price. If the content for a new cache includes an existing cache as a prefix, only the incremental portion is billed for cache creation (i.e., the number of new cache tokens minus the number of existing cache tokens). For example, if you have an existing 1,200-token cache (Cache A) and you use a new request to cache 1,500 tokens of content (Content AB), the first 1,200 tokens are billed as a cache hit at 10% of the standard price. The new 300 tokens are billed for cache creation at 125% of the standard price. The cache_creation_input_tokens parameter specifies the number of tokens used for cache creation. Cache hit : Billed at 10% of the standard input token price. The cached_tokens parameter specifies the number of cached tokens. Other tokens : Tokens that are neither a cache hit nor used for cache creation are billed at the standard input token price. Exception : The following models do not follow the general ratios above. For specific pricing, see the Model Studio console. qwen3.8-max, qwen3.8-max-0902, and qwen3.8-2.4t-a95b: Cache creation is billed at 125% of the standard input token price, but the cache hit price is not 10% of the standard input token price. qwen3.8-flash: The cache creation price is not 125% of the standard input token price , and the cache hit price is not 10% either. Both ratios vary by region. ",
        "implicitBilling": "Billing No additional fees are charged for enabling the implicit cache mode. When a request hits the cache, the input tokens from the cache hit are billed as cached_token . The discount rate for these tokens varies by model. Input tokens that do not hit the cache are billed as standard input_token . Output tokens are billed at the original price. For models other than deepseek-v4.1-flash, deepseek-v4.1-flash-1017, deepseek-v4-pro, deepseek-v4-pro-0813, deepseek-v4-flash-0731, qwen3.8-max, qwen3.8-max-0902, qwen3.8-flash, qwen3.8-2.4t-a95b, and qwen3.8-omni-flash: The unit price of cached_token is 20% of the input_token unit price. qwen3.8-omni-flash: Cache-hit input tokens are billed at a fixed unit price. For regional prices, see Model pricing . deepseek-v4-pro: The unit price of cached_token is not 20% of the input_token unit price. For specific pricing, see the Model Studio console. deepseek-v4.1-flash, deepseek-v4.1-flash-1017, deepseek-v4-pro-0813, and deepseek-v4-flash-0731: The unit price of cached_token is 10% of the input_token unit price. For deepseek-v4.1-flash-1017 , this applies in all six regions listed above during both peak and off-peak periods, using the input unit price for the same region and period. qwen3.8-max, qwen3.8-max-0902, qwen3.8-flash, and qwen3.8-2.4t-a95b: The unit price of cached_token is not 20% of the input_token unit price. For specific pricing, see the Model Studio console. GLM (deployed on Alibaba Cloud Model Studio): The cached_token ratio varies by region. For specific pricing, see the Model Studio console. For glm-5.3, glm-5.3-prime, glm-5.2, and glm-5.2-fast-preview, the ratio is 20% in Singapore and under the US service deployment scope in US (Virginia), and 25% in other regions. For glm-5.1, the ratio is 18.57% in Singapore and 20% in other regions. For glm-5, the ratio is 20% . ",
        "singapore": "The following models are available in the International deployment scope. Qwen Max: qwen3.8-max, qwen3.8-max-0902, qwen3.7-max, qwen3.7-max-2026-05-20, qwen3.7-max-2026-06-08 Qwen Open-source: qwen3.8-2.4t-a95b, qwen3.8-27b Qwen Plus: qwen3.7-plus, qwen3.7-plus-2026-05-26, qwen3.6-plus, qwen3.5-plus, qwen3.5-plus-2026-04-20, qwen-plus Qwen Flash: qwen3.8-flash, qwen3.7-flash, qwen3.7-flash-2026-07-15, qwen3.6-flash, qwen3.5-flash, qwen-flash Qwen Coder: qwen3-coder-flash Qwen VL: qwen3-vl-plus "
      },
      "https://inference-docs.cerebras.ai/models/qwen-3.8-27b.md": {
        "terms": "Model ID: `qwen-3.8-27b`. Context window: 64K tokens (65,536) for Free Trial and 128K tokens (131,072) for paid tiers and trial customers. Maximum output: 32K tokens (32,768) for Free Trial and 40K tokens (40,960) for paid tiers and trial customers. Pricing: $0.99 per million input tokens and $1.49 per million output tokens. Free Trial rate limits: 5 requests per minute, 30K uncached tokens per minute, 90K total tokens per minute, and 1M tokens per day. Developer rate limits: 300 requests per minute, 150K uncached tokens per minute, 750K total tokens per minute (temporarily increased from 450K), and no daily token limit. Modality: multimodal. Accepts text and base64-encoded PNG or JPEG image inputs and produces text output. Maximum images per request: 2 for Free Trial, 10 for Developer and Enterprise accounts using Shared Inference. Maximum request payload: 10 MiB. Capabilities: Image Inputs, Reasoning, Streaming, Sampling Controls, Structured Outputs, Tool Calling, Parallel Tool Calling, and Prompt Caching. Reasoning defaults to `high`. Set `reasoning_effort` to `none` to disable it. `clear_thinking` defaults to `false`, which preserves prior assistant reasoning supplied in conversation history. The `hidden` reasoning format is not supported. See the [Structured Outputs guide](https://inference-docs.cerebras.ai/capabilities/structured-outputs.md) for strict schema support and limitations. > [!NOTE] > > Qwen 3.8 27B is available through both Shared Inference and [Dedicated Inference](https://inference-docs.cerebras.ai/dedicated/overview.md#supported-models). Use `qwen-3.8-27b` with Shared Inference or your assigned endpoint ID with Dedicated Inference."
      },
      "https://www.cerebras.ai/pricing": {
        "row": [
          "[QWEN]Qwen 3.8 27B",
          "~1,850 tokens/s",
          "$$0.99/M tokens",
          "$$1.49/M tokens"
        ],
        "billing": "Features, models, capacity, and performance are subject to availability and applicable terms. Performance varies by model and configuration. * For development, evaluation, and experimentation; not intended for production use. ** Available by agreement. *** Add a valid payment method to receive a one-time $5 promotional credit. The credit expires 30 days after activation. You will not be charged or automatically enrolled in paid usage. API and Playground access will pause when the credit expires or is exhausted unless you separately purchase PayGo credits. Promotional credits are non-transferable, have no cash value, and may be withheld or revoked in cases of fraud, abuse, or duplicate accounts. "
      }
    },
    "sourceReviews": {
      "https://inference-docs.cerebras.ai/models/qwen-3.8-27b.md": {
        "reviewedAt": "2026-11-02T00:34:40.110Z",
        "sourceSha256": "3b93726291c81d849199fb74b726e1dc3c034ad61a0b3be74c6d5b374c655ae1",
        "evidenceDirectory": "/opt/aipricing/data/control/evidence/data-cerebras-qwen-20261025-source-propagation/5b51c06a/",
        "scope": "Official source projection only: link normalization and Shared/Dedicated deployment note; no price, entitlement, limit, billing or narrative verification clock advanced."
      },
      "https://www.alibabacloud.com/help/en/model-studio/model-pricing": {
        "reviewedAt": "2026-11-04T02:19:21.860088+00:00",
        "sourceSha256": "7bade3dab569b738b1534fa58d1e6db14d2213667c01cd2ff1ca530a0654b6d5",
        "evidenceDirectory": "/opt/aipricing/data/control/artifacts/aa4d6b01-d288-444f-afb3-c841fb73868b",
        "scope": "Reviewed exact International alias rates, promotion, tiers and quota change: Qwen3.6-Flash now has no free quota; Qwen3.7-Plus 20% promotion remains. Cache modes and other projections unchanged."
      }
    }
  },
  "currentSourceCheck": {
    "checkedAt": "2026-11-12T01:16:36.389Z",
    "state": {
      "reviewedSubsetOk": false,
      "allCurrent": false,
      "sources": {
        "https://www.alibabacloud.com/help/en/model-studio/models": {
          "ok": true,
          "status": 200,
          "changed": false
        },
        "https://www.alibabacloud.com/help/en/model-studio/model-pricing": {
          "ok": true,
          "status": 200,
          "changed": false
        },
        "https://www.alibabacloud.com/help/en/model-studio/context-cache": {
          "ok": true,
          "status": 200,
          "changed": true
        },
        "https://inference-docs.cerebras.ai/models/qwen-3.8-27b.md": {
          "ok": true,
          "status": 200,
          "changed": false
        },
        "https://www.cerebras.ai/pricing": {
          "ok": false,
          "status": 403,
          "changed": false
        },
        "https://qwen.ai/qwenchat": {
          "ok": false,
          "status": 200,
          "changed": false,
          "error": "HTTP 200 returned only an app shell. Subscription price, limits and model access remain unknown."
        },
        "https://chat.qwen.ai/": {
          "ok": false,
          "status": 200,
          "changed": false,
          "error": "HTTP 200 returned no meaningful server-rendered plan content. No free-plan or model entitlement is inferred."
        }
      }
    }
  }
}