跳至主要內容

模型詳情

claude-fable-5

由 Anthropic 提供
隨用隨付

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins. It is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.

模型規格

上下文長度
1M
最大輸出
128K
輸入/輸出模態
文字 / 圖片
發布日期
2026-06

02

API 端點

單一 MixRoute 閘道,OpenAI 相容

  • Anthropic Messages /v1/messages POST
  • OpenAI-compatible /v1/chat/completions POST

03

價格

固定費率,單位:/1M Tokens

輸入

$10.0000 /1M Tokens

補全

$50.0000 /1M Tokens

快取讀取

$1.0000 /1M Tokens

快取建立

$12.5000 /1M Tokens

05

選型摘要

快速判斷是否適合你的工作負載

What is this model good for?

Autonomous knowledge work and coding with 1M context

Use Claude Fable 5 for long-running, complex, and asynchronous tasks. It supports text, image, and file inputs with a 1M-token context window, and self-corrects through verification loops.

What should you check before using it?

Test autonomous task execution and verification

Fable 5 is built for tasks that previously required frequent human check-ins. Test your multi-step workflows and verify the self-correction behavior meets your quality requirements.

Why use it through MixRoute?

Use the compatible endpoint with stable model ID

Use the confirmed compatible endpoint with model ID claude-fable-5 through MixRoute.

08

Token 成本估算

基於本頁價格的即時估算,非實際帳單

同一前綴被重複讀取的輸入占比,最高 100%

單一端點,可驗證的決策

使用相同的請求格式測試此模型與替代路由

從真實工作負載開始,再由品質、總成本與故障條件決定是否導入正式環境流量。