anthropic
Anthropic: Claude Fable 5.1 (batch)
anthropic/claude-fable-5.1:batch
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to its OpenRouter catalog listing, anthropic/claude-fable-5.1:batch is an Anthropic text-output model that accepts text, image, and file inputs across a one-million-token context window. Reasoning is mandatory, with a high default effort and five selectable effort levels. The catalog description claims broad gains over Claude Fable 5, especially in agentic coding, long-running agentic workflows, and knowledge work, and lists arena and index measurements; these are source-reported claims rather than independent verification. An independent model card was not available in this source pack.[1]
Strengths
- The catalog lists a one-million-token context window with text, image, and file inputs, suiting large or multimodal payloads.[1]
- Reasoning effort is tunable across five levels, and the listing supports tools, structured outputs, response format, and verbosity parameters.[1]
- The catalog description claims the largest improvements over its predecessor in agentic coding and long-running workflows, a vendor-stated capability rather than a measured result.[1]
Limitations
- Reasoning is mandatory and cannot be disabled, which may not suit latency-sensitive or trivial workloads.[1]
- Evidence is catalog-only: no independent model card was supplied, and the listing does not explain what the batch variant changes, so workload validation is needed.[1]
- Output is text-only, and fields such as knowledge cutoff are unset in the listing; these are unknowns, not confirmed gaps.[1]
Where to use it
- Potentially a fit for long-document or multimodal analysis given the large context and image/file inputs; validate on real workloads first.[1]
- Editorially suggested for agentic coding and knowledge-work pipelines, matching the catalog's claimed strengths, with effort adjustable via reasoning_effort.[1]
- Structured-output and tool-calling integrations, since the listing advertises the corresponding parameters.[1]
Sources
- [1] OpenRouter catalog · Anthropic: Claude Fable 5.1 (batch)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- anthropic/claude-fable-5.1:batch
- Canonical ID
- anthropic/claude-fable-5.1-20260831
- Creator
- anthropic
- Added to OpenRouter
- 01.09.2026
- Context length
- 1,000,000
- Modality
- text+image+file->text
- Input modalities
- text, image, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $5 / out $25
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | AA — next 20% of the cohort | reasoning: mandatory · default high · efforts: max, xhigh, high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | SS — top 10% of the cohort | — |
| Agents | SS — top 10% of the cohort | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default high · efforts: max, xhigh, high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 50 | AA — next 20% of the cohort | 13.11.2026 |
| Artificial Analysis | Coding index | 80.7 | SS — top 10% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 57.2 | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 57.1% · rank 3 | 1,304Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · godotgamedevwin rate 60.7% · rank 1 | 1,307Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · htmlslideswin rate 56.5% · rank 1 | 1,394Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 56.3% · rank 7 | 1,257Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · python-pptxslideswin rate 60.8% · rank 1 | 1,308Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · spreadsheetwin rate 70.4% · rank 1 | 1,426Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · webappswin rate 58.2% · rank 2 | 1,316Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 63.1% · rank 8 | 1,391Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 65% · rank 5 | 1,318Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 57.5% · rank 9 | 1,331Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 62.4% · rank 5 | 1,346Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 59.5% · rank 7 | 1,366Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 56.6% · rank 9 | 1,294Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 59.9% · rank 13 | 1,333Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 55.2% · rank 13 | 1,306Elo | SS — top 10% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Anthropic | 1,000,000 | $5 | $25 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.