Claude Fable 5.1
Claude Fable 5.1 is a large language model made by Anthropic, added to the catalog on 1 Sep 2026. It has a context window of 1,000,000 tokens and costs $10.00 per 1M input tokens and $50.00 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: long code refactors, agentic coding workflows and front-end development tasks.
Price checked ยท source: OpenRouter
What Claude Fable 5.1 is
Claude Fable 5.1 is an Anthropic model that accepts text, images, and files and produces text. Its context window holds up to 1,000,000 tokens, and it can generate outputs of up to 128,000 tokens. The catalog lists support for reasoning, tools, structured outputs, and response-format controls. These details describe its input types, output type, context capacity, and supported interaction options.
The provider description identifies agentic coding, long-running agentic workflows, knowledge work, long code refactors, and front-end work as areas of focus. These facts make the model suited to tasks involving substantial text or files, code changes, and written results. A context window of 1,000,000 tokens can hold a large amount of supplied material in one context, while the stated output limit leaves room for lengthy text responses. It also accepts images, though its listed output remains text. Tool support may be relevant for workflows that use tools, while structured outputs and response-format support apply when a task specifies an output structure. Reasoning is also listed as a supported capability. The listed focus areas cover both software-oriented work and broader knowledge tasks, rather than limiting the model to a single kind of request. The catalog does not specify particular programming languages, file formats, image-processing functions, or tool integrations, so suitability depends on the content and workflow provided.
Key features
- Accepts text, image, and file inputs
- Produces text output
- Has a 1,000,000-token context window
- Supports tools, reasoning, and structured outputs
- Supports response-format controls
Typical uses
- Long code refactors
- Agentic coding workflows
- Front-end development tasks
- Knowledge work with extensive context
- Working with text, image, and file inputs
Claude Fable 5.1 pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $10.00 | $5.00 |
| Output, per 1M tokens | $50.00 | $25.00 |
| Cached input read, per 1M tokens | $0.25 | $0.125 |
| Cache write, per 1M tokens | $12.50 | $6.25 |
| Web search, per search | $0.01 | $0.01 |
| Variant | Model id |
|---|---|
| Batch | anthropic/claude-fable-5.1:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 1 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.020 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.290 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.400 |
| Read a 300-page contract set150,000 in / 1,500 out | $1.58 |
Claude Fable 5.1 specifications
| Model id | anthropic/claude-fable-5.1 |
|---|---|
| Version | claude-fable-5.1-20260831 |
| Context window | 1,000,000 tokensAbout 750,000 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 1 Sep 2026 |
| Input types | text, image, file |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Claude Fable 5.1 yet.
Compare Claude Fable 5.1
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.