Claude Fable 5.1
Anthropic's most capable widely released model; thinking always on (adaptive, effort low..max, default high); forced tool_choice any/tool returns 400; no prefill; 30-day data retention required (no ZDR unless authorized); no Priority Tier. Batch $5/$25.
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Knowledge cutoff
- 2026-06
- Input
- text, image, pdf
- Output
- text
- License
- proprietary
- Pricing
- input: $10 · output: $50 · cache read: $0.25 (per 1M tokens (USD); Batch API 50% off) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Anthropic API (Claude API) | claude-fable-5-1 | https://api.anthropic.com/v1/messages | docs |
| AWS Bedrock (Messages API / Mantle) | anthropic.claude-fable-5-1 | — | docs |
| Google Cloud Vertex AI | claude-fable-5-1 | — | docs |
| Microsoft Foundry (Azure) | claude-fable-5-1 | — | docs |
| Claude Platform on AWS | claude-fable-5-1 | — | docs |
| OpenRouter | anthropic/claude-fable-5.1 | openrouter.ai/anthropic/claude-fable-5.1 | — |
| Web app | — | claude.ai | — |
Notable capabilities (5)
- Scientific discovery (protein design): In Anthropic's launch examples, its protein designs reached about 10x higher binding affinity than competition winners, with a hit rate near 50%. source
- Rare-bug hunting: Anthropic reports it found the cause of a one-in-a-million crash that engineers had not explained for years. source
- Top CursorBench score: Scored 73.4% on CursorBench 3.2.0 at max effort, which Cursor called the most capable model it had run. source
- FIRST Preserved thinking and content provenance: Thinking blocks are bound to the model and the conversation, and editing earlier turns invalidates them. Also adds per-message effort, turn-scoped system messages and content provenance. source
- Cheaper cache reads: Cache reads cost $0.25/MTok (0.025x input). Anthropic cites up to 45% savings on agentic work compared with Fable 5. source
Best for the hardest reasoning and long-horizon agentic work (coding, research, documents/spreadsheets/slides, computer use). Successor to Claude Fable 5 at the same price with cheaper cache reads. Same model is offered as Claude Mythos 5.1 to Project Glasswing participants. Handle stop_reason: "refusal" (safety classifiers) and consider the server-side fallbacks parameter.
curl https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_API_KEY" -H "anthropic-version: 2023-06-01" -H "content-type: application/json" \
-d '{"model":"claude-fable-5-1","max_tokens":16000,"messages":[{"role":"user","content":"Hello"}]}'
Sources:
- Model page: https://platform.claude.com/docs/en/models/fable-5-1/overview
- Announcement: https://www.anthropic.com/claude-fable-and-mythos-5-1
- Pricing: https://platform.claude.com/docs/en/about-claude/pricing
- Models overview: https://platform.claude.com/docs/en/about-claude/models/overview
- Deprecations: https://platform.claude.com/docs/en/about-claude/model-deprecations
Other Anthropic models
Claude Sonnet 5.5 · Claude Opus 5.5 · Claude Mythos 5.1 · Claude Haiku 4.5 · Claude Opus 5 · Claude Sonnet 5 · Claude Fable 5 · Claude Opus 4.8 · Claude Opus 4.7 · Claude Sonnet 4.6 · Claude Opus 4.6 · Claude Opus 4.5 · Claude Sonnet 4.5 · Claude Opus 4.1 · Claude Sonnet 4