Anthropic language model
Claude Fable 5.2
Anthropic's Claude model for demanding reasoning and long-horizon agentic work, released as the successor to Fable 5.1. It costs less than 5.1 on input, output and cache, at the same context window; Anthropic points most workloads to the cheaper Opus 5.5.
01
price
input tokens
output tokens
cached input
per 1M tokens. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
- cache hits bill at $0.20 per 1M tokens (0.025x input); cache writes at $10 (5-minute tier) or $16 (1-hour 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
what real work costs
| workload | cost |
|---|---|
| one chat reply 3,000 tokens in, 500 out | $0.04 |
| summarise a 100-page report 50,000 tokens in, 1,500 out, one request | $0.46 |
| 1,000 classification calls 500 tokens in, 20 out, per call | $4.80 |
| coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache | $18.40 |
| same session, cached 85% of input read from the prompt cache, the rest written to it | $5.74 |
at the listed rate. token counts are typical sizes, not measurements.
03
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 $0.2/M
- weights
- closed
- released
- November 9, 2026
- knowledge cutoff
- June 2026
- status
- live
- model id
claude-fable-5-2
integration notes
- tool_choice of type "any" or "tool" returns a 400 error; use "auto" with strict tool use or JSON outputs for schema-valid results.
- setting a non-default temperature, top_p or top_k, or disabling thinking, returns a 400 error.
- editing system, tools or an earlier turn invalidates later thinking blocks; on every account the next request fails with 400.
04
benchmarks
as published by the maker; not measured by octomind.
05
when to pick it
pick it if
- Opus 5.5 at higher effort still falls short on your evals
- you run Fable 5.1 today and want lower rates on the same window
- you run long agent sessions; cache hits bill at 2.5% of input
skip it if
- Opus 5.5 covers your workload at half the per-token price
- your code forces tool use, prefills replies, sets temperature or edits earlier turns; all return errors
06
where it sits on price
blended price $16/M at 3 input tokens per output token: 41 live language models cost less, 2 cost more.
- Claude Opus 5.5 $8/M
- Muse Wonder 1.0 $8/M
- Claude Fable 5.2 $16/M
- Claude Fable 5.1 $20/M
- GPT-6 Astra $20/M
07
use Claude Fable 5.2 in octomind
one octohub login reaches every model in the catalog. pick this one per run, per session, or as your default.
octomind login
octomind run -m octohub:claude-fable-5-2/model octohub:claude-fable-5-2[model]
name = "octohub:claude-fable-5-2"08
compare Claude Fable 5.2
- Claude Fable 5.2 vs Claude Fable 5.1
- Claude Fable 5.2 vs Claude Opus 5.5
- Claude Fable 5.2 vs GPT-6 Astra
- Claude Fable 5.2 vs Gemini 4 Argon
- Claude Fable 5.2 vs Muse Wonder 1.0
09
similar models
nearest live models by listed input price.
- Claude Fable 5.1 $10/M input
- GPT-6 Astra $10/M input
- MiMo V2.6 Pro UltraSpeed $4.35/M input
- Claude Opus 5.5 $4/M input
10
earlier versions
retired models retained for historical reference.
11
Claude Fable 5.2 faq
how much does Claude Fable 5.2 cost?
Claude Fable 5.2 lists at $8/M input, $40/M output, $0.2/M cached input per 1M tokens. a typical coding-agent session (2M tokens in, 60,000 out) comes to $18.40, or $5.74 when 85% of the input is read from the prompt cache. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
what is the context window of Claude Fable 5.2?
1M tokens, ≈ 1,500 pages of prose or 100,000 lines of code. a single reply can run to 128k tokens.
does Claude Fable 5.2 accept images?
yes. it takes text and images as input and returns text.
is Claude Fable 5.2 open source?
no. Claude Fable 5.2 is a closed-weights model, available only through Anthropic's api and hosted gateways such as octohub.
when was Claude Fable 5.2 released?
November 9, 2026, by Anthropic.
is Claude Fable 5.2 free?
no. Claude Fable 5.2 bills per token at $8/M input, $40/M output, $0.2/M cached input per 1M. octomind's free plan reaches it pay as you go from credits, so you pay only for the tokens you use, at the provider price. credits carry a 3% top-up fee.
how do i use Claude Fable 5.2 in octomind?
run octomind login once, then octomind run -m octohub:claude-fable-5-2. inside a running session, /model octohub:claude-fable-5-2 switches to it without losing context.
use Claude Fable 5.2 in octomind
choose a model when you start, then switch mid-session when the work changes.