Amux AI

Anthropic: Claude Fable 5.1

Active

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.

Input:
Output:
Context length:
1M
Max output:
128K
Published:
2026-09-02
toolsreasoningstructuredOutputstreamingvisioncaching

Providers

Same model, different providers. Automatic routing spreads requests across healthy providers by default, or ranks them by price, latency and more.

Provider
Officialamazon-bedrock$10/1M tokens$50/1M tokens
Read$0.25/1M tokensWrite 5m$12.5/1M tokensWrite 1h$20/1M tokens
1M———
Official30% offanthropic$10$7/1M tokens$50$35/1M tokens
Read$0.25$0.175/1M tokensWrite 5m$12.5$8.75/1M tokensWrite 1h$20$14/1M tokens
1M—2.5s24 tps
Value85% offLowestamux-special$10$1.5/1M tokens$50$7.5/1M tokens
Read$0.25$0.0375/1M tokensWrite 5m$12.5$1.875/1M tokensWrite 1h$20$3/1M tokens
1M—10.1s1.26K tps
Official70% offamuxai$10$3/1M tokens$50$15/1M tokens
Read$0.25$0.075/1M tokensWrite 5m$12.5$3.75/1M tokensWrite 1h$20$6/1M tokens
1M—3.9s22.96K tps

Availability

24 hours · 11/13–11/18

Success rate of requests sent by the Amux AI gateway to each provider. Client errors are excluded.

Tok/s

24 hours · 11/13–11/18

Average output speed of streaming requests, in tokens per second (TPS).

TTFT

24 hours · 11/13–11/18

Average time to first token (TTFT) of streaming requests, measured from request dispatch to the first token received.

Activity

24 hours · 11/13–11/18

Relative request activity over time, broken down by serving provider. Indexed to the peak within the selected range (= 100); reflects trends and provider share, not absolute volume.

Related models

More models from Anthropic

Anthropic: Claude Fable 5.21M contextfrom $1.2 / M tokens3 providersAnthropic: Claude Fable 5.2 is built for difficult reasoning and long-term agent tasks. Typical uses include running agent sessions for hours, multi-step in-depth research, and analysis work throughout the entire process to completion of a document, spreadsheet, or presentation.
Anthropic: Claude Haiku 5.51M contextfrom $0.015 / M tokens4 providersAnthropic: Claude Haiku 5.5 is Anthropic’s most affordable, fastest and most powerful small form factor model yet, built for high-volume, cost-sensitive workloads. It handles summarization, reduction, database query, classification, and subagent encoding tasks with low latency, making it particularly useful in real-time customer support, browser usage, and other speed-critical applications.
Anthropic: Claude Sonnet 5.51M contextfrom $0.1 / M tokens5 providersAnthropic: Claude Sonnet 5.5 is Anthropic’s upgraded Sonnet-class model that delivers greater performance than Claude Sonnet 5 while running more than 30% faster and at a lower cost for many workloads. Designed for agent-based coding, tool usage, and everyday professional tasks, it's ideal for developers and teams building fast and powerful AI agents.