Claude Fable 5.1: API price, context window and how to connect

Claude Fable 5.1 by Anthropic: $10 per million input tokens, $50 per million output tokens, a 1M-token window. What it is good for, what to compare it with and how to connect it in SKILLOK.

Updated Copy as Markdown
In this article

In short#

An improvement on Claude Fable 5 with the biggest gains in agentic coding, long-running autonomous tasks and knowledge work: large refactors, front-end and visual tasks. The most expensive Anthropic model in the catalog.

Specifications#

Provider Anthropic
Released 2026-09-01
Context window 1M tokens
Accepts text, images, files
Answers with text
Reasoning mode yes
Tool calling yes
Open weights no
Identifier anthropic/claude-fable-5.1

Price#

Per 1M tokens In dollars
Input (question, context) $10
Output (answer) $50

For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about $0.9. Models in reasoning mode spend more tokens on an answer than the text shows: the reasoning is paid for too.

What it is good for#

  • Long autonomous agent tasks
  • Large code refactors
  • Front-end and visual layout

Similar models#

Catalog models with the same kind of output, closest in the price of a typical request.

Model Input Output Window Price
Claude Opus 5 $5 $25 1M 2× cheaper
Claude Opus 5.5 $4 $20 1M 2.5× cheaper
Qwen3.8 Max Prime $4 $12 1M 3.6× cheaper
GPT-6.1 Sol $2 $10 1.05M 5× cheaper
GPT-6.1 Sol Pro $2 $10 1.05M 5× cheaper

Other Anthropic models#

How to connect in SKILLOK#

Claude Fable 5.1 works through OpenRouter: add an OpenRouter key in Settings → AI and pick the anthropic/claude-fable-5.1 model. It then becomes available in Space AI, in tasks and to the repository agent. In detail — Connecting a model in SKILLOK.

Where the data comes from#

Prices, the context window and capabilities come from the public OpenRouter catalog as of 2026-10-19. A provider may change the price — the exact figure is always on the model's OpenRouter page.

Was this helpful?