Claude Fable 5.1
Availableanthropic/claude-fable-5.1Anthropic's most capable model for long, agentic work: coding, science and computer use. Adaptive thinking is always on.
- Chat
- 1M context
- 128K max output
- Vision
- Tools
Pricing
- Input
- $10 / 1M tokens
- Output
- $50 / 1M tokens
- Cached input
- $0.25 / 1M tokens
What it costs
A typical request: 2,000 tokens in, 500 out$0.045
1,000 of those requests$45.00
Performance on SparrowCodes
Measured from real requests over the last 7 days.
No traffic yet. Speed, latency and success rate appear here once this model has served requests on SparrowCodes; we don't show estimates.
Official benchmarks
Scores published by the model's maker, under their test conditions.
- Terminal-Bench 4.055.8%
- Terminal-Bench-Science 0.152.6%
- GDPval-AA v21853 Elo
- OSWorld 2.0 · partial77.9%
- OSWorld 2.0 · strict41.7%
- Humanity's Last Exam · no tools60.9%
- Humanity's Last Exam · with tools65.0%
- AutomationBench31.4%
- CursorBench 3.2.073.4%
- FrontierCode 1.1 (Main)50.3%
- CursorBench 4.051.8%
- GDPval-AA v2.11735 Elo
- OSWorld 2.1 · partial80.7%
- Chartography · with tools88.4%
Source: Anthropic: Claude Fable 5.1 announcement (2026-09-15)
Source: Anthropic: Claude Opus 5.5 announcement (as reported there) (2026-09-22)
Specifications
- Type
- Chat
- Served by
- Anthropic
- Context window
- 1,000,000 tokens
- Maximum output
- 128,000 tokens
- Input types
- Text, Image
- Tool calling
- Supported
Use it
curl https://api.sparrowcodes.com/v1/chat/completions \
-H "Authorization: Bearer $SPARROW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-fable-5.1",
"messages": [{"role": "user", "content": "Explain rate limiting in one paragraph."}]
}'Set "model" to anthropic/claude-fable-5.1. The response includes its exact cost.