---
last_updated: 2026-11-22
source_url: https://opper.ai/anthropic/claude-fable-5-1
title: "Claude Fable 5.1 by Anthropic"
description: "Claude Fable 5.1 is Anthropic's frontier model for agentic coding, knowledge work, and long-running problem solving, with a 1M token context and 128K output."
---

# Claude Fable 5.1

By [Anthropic](https://opper.ai/anthropic).

Released 1 Sep 2026, 39 days after [Claude Opus 5](https://opper.ai/anthropic/claude-opus-5) · [Announcement](https://platform.claude.com/docs/en/models/fable-5-1/overview) · [All Anthropic releases](https://opper.ai/model-releases/anthropic)

Claude Fable 5.1 arrived on September 1, 2026 as the successor to Claude Fable 5 at the top of Anthropic's generally available lineup. It is the same model as Claude Mythos 5.1, which Anthropic distributes only through trusted access programs with safeguards tailored to vetted cybersecurity and life sciences work, so Fable 5.1 is the broadly available form of that model. It keeps the 1 million token context window and 128K output ceiling, with image input, PDF handling, tool use, structured output, and adaptive thinking that scales effort to the task.

The release is mostly about agentic depth. Anthropic reports 55.8% on Terminal-Bench 4.0 against 42.0% for Fable 5, 52.6% on Terminal-Bench-Science 0.1 against 24.7%, 31.4% on AutomationBench against 17.1%, 73.4% on CursorBench 3.2.0, 41.7% on the strict OSWorld 2.0 computer-use setting, and 60.9% on Humanity's Last Exam without tools. Anthropic also cites a large gain on its contract redlining benchmark and describes the model as steadier than Fable 5 through long stretches of unattended work.

Fable 5.1 suits long multi-step engineering sessions, research-grade analysis, and agents that operate terminals and computers over many hours. Its cybersecurity safeguards now block about 60% fewer false positives than before, and the model can be used to find software vulnerabilities, though not to develop exploits.

## Available routes

Claude Fable 5.1 runs on 3 different routes through the Opper gateway. Prices are per 1M tokens. Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=claude-fable-5-1.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Anthropic](https://opper.ai/provider/anthropic) | `anthropic/claude-fable-5-1` | US (United States) | Abuse monitoring | No | $10.00 | $50.00 | $0.25 ($12.50 write) |
| [Azure](https://opper.ai/provider/azure) | `azure/claude-fable-5-1` | Multi-region | Abuse monitoring | No | $10.00 | $50.00 | $0.25 ($12.50 write) |
| [Google Cloud](https://opper.ai/provider/google) | `vertexai/claude-fable-5-1` | Multi-region | Abuse monitoring | No | $10.00 | $50.00 | $0.25 ($12.50 write) |

## Key info

- Model id: `claude-fable-5-1` (routes across Anthropic, Azure, Google Cloud)
- Input: Text, Image, Files
- Output: Text
- Features: Reasoning, Tools, Structured output, PDF input
- Context window: 1M
- Max output: 128K
- Input price: $10.00 per 1M tokens ($0.25 cache read · $12.50 write)
- Output price: $50.00 per 1M tokens
- Released: 1 Sep 2026
- US residency available on Anthropic
- Zero data retention with abuse monitoring
- No training by default

## Data handling per route

Each route hosting Claude Fable 5.1 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### Anthropic — United States

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. US; SCCs.

- Zero data retention: With abuse monitoring, window not stated.
- Training: No training on customer data.
- Logging: Abuse monitoring
- Abuse monitoring: On by default, holds flagged content, 730 days, a person can view samples
- Caching: Content cached for replay
- Transfer mechanism: SCCs

Verified by Opper on 2026-09-17.

### Azure — Multi-region

Zero data retention with abuse monitoring: prompts and outputs are kept for up to 30 days for abuse monitoring only, and are not used for training. No training on customer data. GLOBAL; SCCs.

- Zero data retention: With abuse monitoring, 30-day window.
- Training: No training on customer data.
- Logging: Abuse monitoring (30-day retention)
- Abuse monitoring: On by default, holds flagged content, 730 days, a person can view samples
- Caching: Content cached for replay
- Transfer mechanism: SCCs

Verified by Opper on 2026-10-09.

### Google Cloud — Multi-region

Zero data retention with abuse monitoring: prompts and outputs are kept for up to 30 days for abuse monitoring only, and are not used for training. No training on customer data. GLOBAL; SCCs.

- Zero data retention: With abuse monitoring, 30-day window.
- Training: No training on customer data.
- Logging: Abuse monitoring (30-day retention)
- Abuse monitoring: On by default, holds flagged content, 90 days, a person can view samples
- Transfer mechanism: SCCs

Verified by Opper on 2026-10-26.

## Best for

Where Claude Fable 5.1 ranks among the models on Opper with a score for each use case (0 to 100).

- [Legal](https://opper.ai/models?use=legal): 54.5, #10 of 53 (Legal tasks and reasoning)
- [Coding](https://opper.ai/models?use=coding): 43.5, #12 of 52 (FrontierCode 2.0 and Terminal-Bench 4.0)
- [Finance](https://opper.ai/models?use=finance): 53.8, #13 of 53 (Finance and accounting)
- [Healthcare](https://opper.ai/models?use=healthcare): 51.2, #13 of 50 (Healthcare and medical)
- [Agents](https://opper.ai/models?use=agents): 56.5, #15 of 93 (Terminal-Bench 4.0 and AutomationBench)

## Benchmarks

Independent benchmark scores via [Artificial Analysis](https://artificialanalysis.ai) ([view on AA](https://artificialanalysis.ai/models/claude-fable-5-1)). Indices and domain scores are out of 100, Omniscience runs from −100 to 100, Briefcase is an Elo rating, and the other evaluation scores are the share of tasks solved.

- Global rank: #14 of 520 LLMs on the [LLM leaderboard](https://opper.ai/llm-leaderboard)
- Tier: Frontier
- Output speed: 64 tok/s
- Intelligence Index: 50.0

### Coding

- FrontierCode 2.0: 36%
- Terminal-Bench 4.0: 55%
- SciCode: 63%

### Agentic & knowledge work

- AutomationBench: 59%
- GDPval: 63%
- GDP.pdf: 28%
- Briefcase (Elo): 1670

### Science & reasoning

- Terminal-Bench Science: 43%
- CritPt (hard): 62%
- HLE Diamond: 60%
- Humanity's Last Exam: 59%
- GPQA Diamond: 94%
- Long-context reasoning: 85%

### Knowledge

- Omniscience: 46.3

### By domain

- Finance & accounting: 53.8
- Legal: 54.5
- Healthcare & medical: 51.2
- Engineering: 57.2
- Economics: 57.3
- Strategy & operations: 58.0

## Get started

Call Claude Fable 5.1 through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Claude Fable 5.1 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai Call Claude Fable 5.1
```

### Or call it directly

OpenAI:

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const completion = await client.chat.completions.create({
  model: "claude-fable-5-1",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);
```

Anthropic:

```javascript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const message = await client.messages.create({
  model: "claude-fable-5-1",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content);
```

Gemini:

```javascript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.OPPER_API_KEY,
  httpOptions: { baseUrl: "https://api.opper.ai/v3/compat" },
});

const response = await ai.models.generateContent({
  model: "claude-fable-5-1",
  contents: "Hello",
});
console.log(response.text);
```

cURL:

```bash
curl https://api.opper.ai/v3/compat/chat/completions \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-fable-5-1",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
```

## Use Claude Fable 5.1 in your apps

Pick your tool to see how to run it on Claude Fable 5.1 through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/claude-fable-5-1)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/claude-fable-5-1)
- [Codex](https://opper.ai/apps/codex/claude-fable-5-1)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/claude-fable-5-1)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/claude-fable-5-1)
- [Aider](https://opper.ai/apps/aider/claude-fable-5-1)
- [Goose](https://opper.ai/apps/goose/claude-fable-5-1)
- [Droid](https://opper.ai/apps/droid/claude-fable-5-1)
- [OpenCode](https://opper.ai/apps/opencode/claude-fable-5-1)
- [Pi](https://opper.ai/apps/pi/claude-fable-5-1)
- [OpenClaw](https://opper.ai/apps/openclaw/claude-fable-5-1)
- [Hermes](https://opper.ai/apps/hermes/claude-fable-5-1)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/claude-fable-5-1)
- [OmniRoute](https://opper.ai/apps/omniroute/claude-fable-5-1)
- [Cursor](https://opper.ai/apps/cursor/claude-fable-5-1)
- [Cline](https://opper.ai/apps/cline/claude-fable-5-1)
- [Continue](https://opper.ai/apps/continue/claude-fable-5-1)
- [Kilo Code](https://opper.ai/apps/kilo-code/claude-fable-5-1)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/claude-fable-5-1)
- [Zed](https://opper.ai/apps/zed/claude-fable-5-1)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/claude-fable-5-1)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/claude-fable-5-1)
- [n8n](https://opper.ai/apps/n8n/claude-fable-5-1)
- [LibreChat](https://opper.ai/apps/librechat/claude-fable-5-1)
- [Open WebUI](https://opper.ai/apps/open-webui/claude-fable-5-1)
- [See all apps](https://opper.ai/apps)

## Other models from Anthropic

- [Claude Opus 5.5](https://opper.ai/anthropic/claude-opus-5-5)
- [Claude Sonnet 5.5](https://opper.ai/anthropic/claude-sonnet-5-5)
- [Claude Fable 5.2](https://opper.ai/anthropic/claude-fable-5-2)
- [Claude Haiku 5.5](https://opper.ai/anthropic/claude-haiku-5-5)
- [Claude Opus 5](https://opper.ai/anthropic/claude-opus-5)
- [Claude Fable 5](https://opper.ai/anthropic/claude-fable-5)
