Claude Fable 5.1: price, context window and specs

What Anthropic says it's for

Per Anthropic's model page, Fable 5.1 extends Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep research, and document, spreadsheet and slide work. Anthropic estimates it costs about 25% less than Fable 5 for typical workloads where usage is billed by token, and up to about 45% less for highly agentic work. Mythos 5.1 is available only through Anthropic's trusted access programs for cybersecurity and life sciences.

Fable 5.1 or Opus 5.5?

Anthropic's models overview says to start with Opus 5.5 for most workloads and use Fable 5.1 for demanding reasoning and long-horizon agentic work, or when your evals on Opus 5.5 at higher effort still fall short. Opus 5.5 costs $4 / $20, less than half of Fable's per-token price. Anthropic's Opus 5.5 announcement claims Opus 5.5 performs at Fable 5.1's level on most work.

Pricing details

• Base: $10 per million input tokens and $50 per million output tokens.
• Prompt caching: 5-minute writes $12.50, 1-hour writes $20, cache reads $0.25.
• Batch API: 50% off ($5 / $25).
• Forced tool use (tool_choice any or tool) returns a 400 error on Fable 5.1. Anthropic suggests strict tool use or structured outputs instead.

Using Fable 5.1 in Claude Code

• Run /model fable or start with claude --model fable. It needs Claude Code v2.1.257 or later, which added Fable 5.1 on 1 September 2026.
• Per the model configuration docs, no Fable model is the default on any plan or provider, so you must select it.
• Depending on your plan, Fable usage can bill to usage credits instead of your included limits. The /model picker then shows "Requires usage credits" and Claude Code asks before billing.
• Requests that Fable's safety classifiers flag, most often in cybersecurity and biology, trigger an automatic fallback to another model.
• Max plans have a separate weekly limit for Fable, on top of the general weekly limit, per Anthropic's help center.

On launch day ClaudeDevs posted that Anthropic had also reset five-hour and weekly limits for all users. It's one of the entries in our Claude reset archive.

Independent benchmarks

Artificial Analysis lists Claude Fable 5.1 (max effort, default fallback) at 53 on its Intelligence Index v4.3.2, at $7.63 per Intelligence Index task, as of 13 October 2026. That's below Opus 5.5's 58 on the same index. In its 12 October post, Artificial Analysis said Fable 5.1 used about 78k output tokens per Intelligence Index task.