Claude Fable 5.1
Point upgrade to Claude Fable 5 from Anthropic, aimed at agentic coding, long-running agentic workflows, and knowledge work. Same 1M context and rack rate as Fable 5.
Cite
Notes
Only stored in your browser.
Context
1M
Weights
Closed
API only
Input
$10
/1M tok
Output
$50
/1M tok
Cache read
$0.25
0.03x input
Cache write
$12.50
1.25x input
Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter
| Reasoning effort | Index | Speed |
|---|---|---|
| Reasoning, max | 53.4 | 67 t/s |
| Reasoning, xhigh | 53.2 | 63 t/s |
| Reasoning, high | 51.2 | 61 t/s |
| Reasoning, medium | 49.1 | 58 t/s |
| Reasoning, low | 47.0 | 56 t/s |
Intelligence Index per reasoning-effort setting, via Artificial Analysis · pricing identical across tiers
Reported on 15 evals across 8 domains - best 100.0% on ProofBench · #1 of 60