Claude Fable 5.1 API
Anthropic's frontier Claude model for ambitious coding, long-horizon agents and enterprise knowledge work. Adaptive thinking is always on, with effort controlling how deeply it reasons.
anthropic/claude-fable-5-1
Top up $20 and we add 50%. That gives you about 1.1M input tokens extra on this model, on us.
Create an accountData retention
Under Anthropic's policy for this model, prompts and outputs are retained for up to 30 days for automated safety monitoring. Content flagged by those checks may be reviewed by trained safety staff. This retention is required by Anthropic, not by Run BiOS.
- Prompts and outputs kept
- Up to 30 days
- Human review
- Possible
- Why
- Anthropic requires safety monitoring of this model's prompts and outputs
Terms updated 14 November 2026
Pricing
USD per 1M tokens| Input | |
| Output | |
| Cached input | |
| Cache write (5m) | |
| Cache write (1h) |
5% off: RunBIOS Startup Program. Promotional price on input, output, cache reads & cache writes. Standard prices shown struck through.
Billed per token with no minimum and no monthly fee. Price your workload
Capabilities and limits
- Context window
- 1M tokens
- Max output
- 125K tokens
- Modality
- text
- Tool calling
- Supported
- Vision
- Supported
- Reasoning
- Always on
- Reasoning effort
- low, medium, high, xhigh, max (default: high)
- Prompt caching
- Supported (platform_managed)
Routing
Run BiOS manages capacity for this model and fails over automatically, so there is nothing to provision and no outage of ours becomes yours.
Not sure which model to use? BiOS Adaptive routes to the best model per request, including this one.
curl https://api.runbios.ai/v1/chat/completions \
-H "Authorization: Bearer $BIOS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-fable-5-1",
"messages": [{ "role": "user", "content": "Hello" }]
}'Existing OpenAI SDK code works by changing the base URL and the key. API overview
Model card
Curated by Run BiOS · benchmark figures, where present, are the card’s own, not our measurements
Claude Fable 5.1 is Anthropic's frontier model for ambitious coding, long-horizon agents and enterprise knowledge work. It handles software projects that span an entire codebase, runs multi-hour jobs across many tools and takes an analysis from the first question to a finished document. It has a 1M-token context window and up to 128K output tokens per request.
Fable 5.1 and Claude Mythos 5.1 are the same underlying model. Fable carries Anthropic's cybersecurity and biology safeguards, which is what makes it available to everyone. Its successor, Claude Fable 5.2, scores higher on every benchmark below at a lower price. Fable 5.1 stays available for work that is already tuned to it.
Capabilities
- Adaptive thinking, always on: the model decides how much to reason on each task and effort is the control. Thinking cannot be switched off on this model. On Run BiOS, Fable 5.1 exposes the
low,medium,high,xhighandmaxreasoning-effort levels and defaults tohigh, the same default Anthropic's API uses. - Long context: a 1M-token context window and up to 128K output tokens per request.
- Multimodal input: text and image input, with text output, with strong vision on dense filings, charts and diagrams.
- Agents and tools: built for multi-hour jobs that span many applications. It plans, uses the tools it needs, recovers when a step fails and keeps you updated without being asked. If it gets stuck, it says what it tried and where.
- Prompt caching: cache reads are priced far below fresh input, which matters most in long agentic sessions.
Benchmark results
Results reported in Anthropic's launch materials for Claude Fable 5.2, which compare Fable 5.1 with its successor and with Opus 5.5. Safeguards on and each model at its highest available effort unless noted.
| Benchmark | Claude Fable 5.1 | Claude Fable 5.2 | Claude Opus 5.5 |
|---|---|---|---|
| FrontierCode 2.0 (agentic coding) | 32.4% (xhigh) | 49.1% (xhigh) | 45.5% |
| FrontierSWE v2 (agentic coding) | 56.3% | 69.9% | 62.3% |
| AutomationBench (business workflows) | 31.4% | 51.4% | 42.5% |
| Terminal-Bench-Science 0.1 (agentic research) | 52.6% | 74.6% | 58.7% |
| OSWorld 2.1 (computer use, offline set, partial credit) | 83.5% | 89.3% | 87.2% |
| Humanity's Last Exam (with tools) | 65.6% | 74.2% | 67.7% |
| Chartography (chart recognition, no tools) | 44.8% | 73.4% | 64.4% |
| AA-Briefcase v1.1 (knowledge work, rubric) | 61.5% | 66.1% | 61.2% |
At launch, Anthropic reported that Fable 5.1 more than doubled Fable 5 on Terminal-Bench-Science and that at low or medium effort it matched or beat Fable 5 at a much lower cost.
Working with the model
Behaviours to plan for:
- Thinking cannot be disabled. A request that asks to turn reasoning off is served with reasoning on at the default effort. Use
loweffort for the fastest and cheapest responses. - Forced tool use is not supported.
tool_choiceofautoandnonework. To make the model call a tool, describe in the prompt when the tool applies. - Sampling is the model's own.
temperatureandtop_pare not adjustable on this model and are ignored if sent. - Thinking is tied to the conversation. Keep conversation history append-only when you replay earlier turns, or the request is refused.
- Some requests are answered by an earlier model. Safety classifiers block a narrow set of high-risk cybersecurity and biology requests, and those are answered by an earlier Claude model instead.
Data retention
Under Anthropic's policy for Fable 5.1, prompts and outputs are retained for up to 30 days for automated safety monitoring and content flagged by those checks may be reviewed by trained safety staff. This retention is required by Anthropic, not by Run BiOS. The data retention notice on this page has the details.
Safety and evaluations
Anthropic's pre-deployment evaluation is documented in the Claude Fable 5.1 and Claude Mythos 5.1 System Card. Anthropic deploys Fable 5.1 with the same biological safeguards as Fable 5 and with cybersecurity safeguards that target a narrow set of high-risk requests, so routine software development and most research work are unaffected.