Anthropic language model
Claude Fable 5.1
live models in this family: Claude Haiku 5.5, Claude Sonnet 5.5, Claude Opus 5.5, Claude Fable 5.2.
Anthropic's Claude model for demanding reasoning and long-horizon agentic work, released as the successor to Fable 5. Claude Fable 5.2 replaces it and costs less on every rate.
01
historical price
input tokens
output tokens
cached input
historical listed price per 1M tokens.
- cache hits bill at $0.25 per 1M tokens (0.025x input), a quarter of Fable 5's $1; cache writes at $12.50 (5-minute tier).
- the full 1M-token window bills at the standard rate, with no long-context surcharge.
- adaptive thinking is always on and cannot be disabled; the effort setting (default high) steers its depth.
02
specs
- provider
- Anthropic
- context window
- 1M tokens — ≈ 1,500 pages of prose or 100,000 lines of code
- max output
- 128k tokens
- input
- text, images
- output
- text
- structured output
- yes — JSON schema
- reasoning mode
- yes
- prompt caching
- yes — cache hits at $0.25/M
- weights
- closed
- released
- September 1, 2026
- knowledge cutoff
- June 2026
- status
- retired 17 November 2026
- model id
claude-fable-5-1
integration notes
- tool_choice of type "any" or "tool" returns a 400 error; use "auto" with strict tool use or structured outputs instead.
- setting a non-default temperature, top_p or top_k, or prefilling the assistant reply, returns a 400 error.
- editing system, tools or an earlier turn invalidates later thinking blocks; on accounts created from 2026-08-31 the next request fails with 400.
03
benchmarks
as published by the maker; not measured by octomind.
04
what it was for
pick it if
- your integration is pinned to 5.1 while you test Fable 5.2
- you run long agent sessions; cache hits bill at 2.5% of input
skip it if
- you are starting new work; Claude Fable 5.2 costs less on every rate at the same window
- your code forces tool use, prefills replies or sets temperature; all return errors
05
compare Claude Fable 5.1
- Claude Fable 5.1 vs Claude Fable 5
- Claude Fable 5.2 vs Claude Fable 5.1
- Claude Fable 5.1 vs GPT-6 Astra
- Claude Fable 5.1 vs Claude Opus 5.5
06
similar models
nearest live models by listed input price.
- GPT-6 Astra $10/M input
- Claude Fable 5.2 $8/M input
- MiMo V2.6 Pro UltraSpeed $4.35/M input
- Claude Opus 5.5 $4/M input
07
Claude Fable 5.1 faq
how much does Claude Fable 5.1 cost?
Claude Fable 5.1 listed at $10/M input, $50/M output, $0.25/M cached input per 1M tokens before it retired on 17 November 2026.
what is the context window of Claude Fable 5.1?
1M tokens, ≈ 1,500 pages of prose or 100,000 lines of code. a single reply can run to 128k tokens.
does Claude Fable 5.1 accept images?
yes. it takes text and images as input and returns text.
is Claude Fable 5.1 open source?
no. Claude Fable 5.1 is a closed-weights model, available only through Anthropic's api and hosted gateways such as octohub.
when was Claude Fable 5.1 released?
September 1, 2026, by Anthropic.
is Claude Fable 5.1 still available?
no. it retired on 17 November 2026. current models in the family: Claude Haiku 5.5, Claude Sonnet 5.5, Claude Opus 5.5 and Claude Fable 5.2.
use Claude Fable 5.1 in octomind
explore the live models in this family above to choose a current replacement.