claude-fable-5.1Anthropic PBC
- api
- chat
- hosting
- US
- model lab
- Anthropic
- weights
- closed
- added
- September 2026
- model id
- anthropic/claude-fable-5.1
capabilities 7/8
2 providers serve claude-fable-5.1. This page is one of them. Compare all endpoints
- input
- $10.00
- output
- $50.00
- cache write
- $12.50
- cache read
- $0.25
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $1.50 |
| 1M in + 100K out | $15.00 |
| 10M in + 1M out | $150.00 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
no measured traffic for this endpoint yet. pricing above is the provider's own
| eval | Score as a share of 100 | /100 |
|---|---|---|
| GPQA Diamond | 93.7 | |
| Coding Index | 81.6 | |
| SciCode | 63.1 | |
| Humanity's Last Exam | 59.1 | |
| Intelligence Index | 53.4 | |
| 5 evals | mean | 70.2 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-09-01.
- retention
- 30 days
- trains on prompts
- no
- hosted in
- US
Terms are the provider's, not Requesty's: routing a request here puts it under them. Anthropic Privacy Policy
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
anthropic/claude-fable-5.1this id pins the anthropic pbc deployment, with no routing and no failover. the managed id on the canonical page routes across all 2 providers instead
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="anthropic/claude-fable-5.1", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models
Claude Fable 5.1 is Anthropic's most capable model, improving on Claude Fable 5 across agentic coding, long running agentic workflows, and knowledge work such as large code refactors, front end and visual code generation, and finance and analysis tasks. It ships a 1M token context window by default with 128K max output, is more token efficient and concise than Fable 5, and supports per message effort control. It is a Mythos class model with robust safeguards.
questions 6
How much does claude-fable-5.1 cost?
What is the context window of claude-fable-5.1?
How does claude-fable-5.1 perform on benchmarks?
What can claude-fable-5.1 do?
How do I use claude-fable-5.1 with the OpenAI SDK?
Can I run claude-fable-5.1 through Requesty?
more from anthropic pbc 8
| endpoint | ctx | in /M |
|---|---|---|
| claude-opus-5 | 1M | $5.00 |
| claude-sonnet-5 | 1M | $2.00 |
| claude-fable-5 | 1M | $10.00 |
| claude-opus-4-8 | 1M | $5.00 |
| claude-opus-4-7 | 1M | $5.00 |
| claude-sonnet-4-6 | 1M | $3.00 |
| claude-opus-4-6 | 1M | $5.00 |
| claude-opus-4-5 | 200K | $5.00 |
call claude-fable-5.1 through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology