Claude Fable 5.1
claude-fable
Claude model for demanding reasoning and long-horizon agentic work
ReasoningTool CallingAttachments
Context Window
1M
Max Output
128K
Temperature
No
Open Weights
No
Knowledge Cutoff
2026-06
Released
2026-09-01
Last Updated
2026-09-01
Modalities
Input:TextImagePDF
→Output:Text
Benchmarks
| Benchmark | Score | Metric |
|---|---|---|
| Terminal-Bench-Science | 52.6 | score |
| Terminal-Bench | 55.8 | score |
| GDPval-AA | 1853 | Elo |
| OSWorld | 77.9 | partial score |
| OSWorld | 41.7 | strict success rate |
| Humanity's Last Exam | 60.9 | score |
| Humanity's Last Exam | 65 | score |
| AutomationBench | 31.4 | pass rate |
| CursorBench | 73.4 | score |
Available Providers (8)
| Provider | Input /1M | Output /1M | Cache Read /1M | Cache Write /1M | Reasoning | Status |
|---|---|---|---|---|---|---|
 Eden AI | Rp 181.290 | Rp 906.446 | Rp 4.533 | Rp 226.612 | effort | — |
 Perplexity Agent | Rp 181.290 | Rp 906.446 | Rp 4.533 | Rp 226.612 | effort | — |
 LLM Gateway | Rp 181.290 | Rp 906.446 | Rp 4.533 | Rp 226.612 | effort | — |
 Aixy | Rp 181.290 | Rp 906.446 | Rp 4.533 | Rp 226.612 | effort | — |
 Merge Gateway | Rp 181.290 | Rp 906.446 | Rp 4.533 | Rp 226.612 | effort | — |
 Tempr Gateway | Rp 181.290 | Rp 906.446 | Rp 4.533 | Rp 226.612 | effort | — |
 CrossModel | Rp 181.290 | Rp 906.446 | Rp 4.533 | Rp 226.612 | effort | — |
 NEAR AI Cloud | Rp 181.290 | Rp 906.446 | Rp 4.533 | — | ✓ | — |