Anthropic · Long and demanding tasks
Claude Fable 5.1
A variant for demanding work where longer processing times and higher costs are acceptable.
- Costs
- $10 input / $50 output per million tokens in standard API mode.
- Speed
- The provider ranks it among the slower models in the Claude family.
- Availability
- Claude API, Amazon Bedrock, Google Cloud and Microsoft Foundry
- Input length
- 1 million tokens; output capped at 128 thousand tokens.
- Inputs
- Text and images → text
Data checked . Published September 1, 2026. Specifications and prices are provided by the vendor; usage recommendations come from the editorial team. We do not yet have our own comparative test of this version.
Ideal use
When to choose it
- Complex tasks with multiple sequential steps
- Working with extensive context and code
Usage boundaries
When to choose another model
- When you need the fastest possible response or the lowest costs.
Traceable supporting sources
Data and measurement sources
Distinguish between the manufacturer's documentation and the results of a specific test. Measurements also depend on the settings and the task set used.
Vendor documentation
Specifications, availability, and termsManufacturer data verified as of the review date. Recommended use is an editorial interpretation.
Open original source ↗Efficiency in practice
With what Claude Fable 5.1 combine
Documents → analysis → verification
A fast model prepares the material, and a stronger model focuses on analyzing it.
Agreement between two models is not proof; the cited inputs are what matters.Next step
Compare the model using your actual task.
A benchmark narrows the selection. A short trial on your data determines the choice.