Vercel AI Gateway 開放使用 Anthropic Claude Fable 5.2
Claude Fable 5.2 now available on AI Gateway
Vercel AI Gateway 開放使用 Anthropic 的 Claude Fable 5.2,提供模型呼叫、用量追蹤與模型回退設定。
- 模型能力:Claude Fable 5.2 面向開放式技術工作,在程式開發、推理與視覺能力上優於先前的 Fable 模型;可無人看管地執行冗長且目標模糊的任務,也能協調較小型模型,或作為其他 Claude 模型的顧問。原文並稱其溝通更清楚、輸出速度更快。
- 推理設定:Effort 可設為 low 至 max,API 預設為 high。
- 資料保留與安全限制:模型啟用了資安與生物學安全分類器,使用時必須接受資料保留;Anthropic 不支援此模型的 Zero Data Retention。提示詞與回覆會保留 30 天,且不會用於訓練 Claude。若團隊已啟用 ZDR,AI Gateway 會回傳錯誤,不會轉送請求。
- 模型回退:若資安分類器拒絕請求,可在
providerOptions.gateway加入models陣列,讓 AI Gateway 依序嘗試其他模型。範例設定會先回退至 Opus 5.5,再至 Sonnet 5.5;此設定適用於各種 AI Gateway API 格式。 - 使用方式與費用:可透過 AI SDK、Chat Completions、Responses、Anthropic Messages API,或連線 AI Gateway 的程式代理呼叫;模型名稱為
anthropic/claude-fable-5.2。在 Claude Code、Codex、Cursor 等工具中使用,需安裝最新版 Vercel CLI 並執行設定。AI Gateway 依照供應商定價,不加價,也不對推論收取平臺費用,包括 BYOK 請求。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Claude Fable 5.2 在 AI Gateway 的接入同時附帶資料保留與安全分類器限制,也提供模型回退設定,呈現實際使用時需考量的部署條件。
Claude Fable 5.2 from Anthropic is now available on AI Gateway.
Fable 5.2 is built for open-ended technical work and improves on earlier Fable models in coding, reasoning, and vision. It can run long, ambiguous tasks unattended, and works as an orchestrator that hands simpler tasks to smaller models, or as an advisor that other Claude models consult on harder problems. It also communicates more clearly and generates output faster than earlier Fable models. Effort runs from low to max, with high as the API default.
Fable 5.2 has cybersecurity and biology safety classifiers enabled. Access to Claude Fable 5.2 requires data retention. Anthropic does not support Zero Data Retention for the model. Prompts and completions are retained for 30 days and are not used to train Claude. If your team has ZDR turned on, AI Gateway returns an error instead of sending the request to Fable 5.2.
To keep requests served when a classifier is triggered, use model fallbacks. Add a models array to providerOptions.gateway, and AI Gateway tries each model in order when the cybersecurity classifier declines a request.
Call it through the AI SDK, the Chat Completions, Responses, and Anthropic Messages APIs, or a coding agent connected to AI Gateway. Use anthropic/claude-fable-5.2 as the model name:
This request falls back to Opus 5.5, then Sonnet 5.5, if the cybersecurity classifier declines it. The models option works the same way on every AI Gateway API format.
To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup:
Try Claude Fable 5.2 in the model playground.
AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more.
AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.
You can view all language models available on AI Gateway.