Claude Fable 5.1
Anthropic · released Sep 1, 2026
- Type
- Closed
- Input
- $10.00
- Output
- $50.00
- Cached
- $0.25
List price · per 1M tokens · Anthropic at 1M context · machine-readable source ↗
Our take
Written Oct 1, 2026Claude Fable 5.1 is a hosted-only model: we list no download for it, so using it means choosing a host. It leads the agentic boards we record, and its weakest measured area is tool use, where it sits in the bottom half of the same field.
Reach for it in agentic sessions where the model has to finish a task and recover when a command fails, or for long-document work where splitting files first is a nuisance. It takes text, images and files alongside the question. Skip it if you need to run the model on your own hardware, or if calling the right tool without inventing one is the core of your workflow.
The case for it
- 1st of 55 on Arena Agent via Max as of 25 Sep 2026, and 1st of 58 on LiveBench via Max effort as of 25 Jun 2026, so it is the one to start with when a task has to be carried through rather than answered.
- 97.01% on LiveBench Mathematics and 91.69% on LiveBench Reasoning at Max effort, both competition-style set-piece tasks rather than open-ended project work.
- The request capacity is large enough that long documents need not be split up first, though reliable recall across all of it is unverified in our data.
- Text, image and file input with written output, so a screenshot or a document does not have to be described in words first.
The case against it
- 24th of 55 on Arena Agent · Tool use via Max as of 25 Sep 2026, an inverse-propensity score for calling the right tool and not inventing one, placing it in the bottom half of that field.
- 15th of 168 on Arena Coding via Max as of 25 Sep 2026, well behind its 3rd of 168 on Arena Text (overall) and 4th of 168 on Arena Creative Writing.
- We list no download for it, so using it means choosing a host; all five hosts list the same rate, so price does not pick one for you.
How good is it?
A closed text model for everyday questions, drafting, coding and multi-step agent work.
- getting answers to everyday questionsArena Text (overall) · 3rd of 168
- drafts, rewrites and editingArena Creative Writing · 4th of 168
- writing and completing codeArena Coding · 15th of 168
- multi-step work it carries out for youArena Agent · 1st of 55
- changing course when you give new instructionsArena Agent · Steerability · 6th of 55
- getting back on track after a step failsArena Agent · Recovery · 2nd of 55
EverydayGeneral questions and everyday reasoning
Arena Text (overall)3rd of 168 · 1501
CodingWriting and fixing code on its own
Arena Coding15th of 168 · 1529
AgenticPlanning, calling tools, staying on task
Arena Agent1st of 55 · 0.138
WritingDrafting and rewriting prose
Arena Creative Writing4th of 168 · 1484
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model20 scoresEvery figure we hold, from 20 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
Anthropic, direct
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Anthropic on 1M of context.
- per 1M tokens
- $10.00 in / $50.00 out
- Context served
- 1M
- Throughput
- ~51 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $10.00 / $50.00checked 4 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AIThrough OpenRouter | $10.00 / $50.00checked 4 hours ago | 1M128K max reply | 45 tok/s | No | No | Unknown |
| Google Vertex AIglobalThrough OpenRouter | $10.00 / $50.00checked 4 hours ago | 1M128K max reply | 62 tok/s | No | No | Unknown |
| AnthropicDirect | $10.00 / $50.00checked 4 hours ago | 1M128K max reply | 51 tok/s | No | Yes30 days | Unknown |
| Amazon BedrockThrough OpenRouter | $10.00 / $50.00checked 4 hours ago | 1M128K max reply | 50 tok/s | No | No | Unknown |
OpenRouter
Microsoft Azure AI
Google Vertex AI
Amazon BedrockAcross the 5 listings we hold: 4 say they do not train on prompts, 0 say they do and 1 does not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Microsoft Azure AIThrough OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIglobalThrough OpenRouter | ✓ | ✓ | ✓ |
| AnthropicDirect | ✓ | ✓ | ✓ |
| Amazon BedrockThrough OpenRouter | ✓ | ✓ | ✗ |
Tool calling: 5 of 5 listings say yes. JSON output: 5 of 5 listings say yes. Strict schema: 4 of 5 listings say yes, 1 says no.
Models people weigh against Claude Fable 5.1
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 5 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images and documents in, text out
- Catalogue slug
- anthropic-claude-fable-5-1