Claude Fable 5.1

Anthropic's fifth-generation flagship, built for long-horizon autonomous work that runs unattended for hours or days across coding, research, and document-heavy professional tasks.

The model is built to keep working unattended for hours or days: planning its own steps, calling tools, recovering when a step fails, and reporting progress. That makes it a fit for feature development across an entire codebase, code review, performance work, and multi-day coding sessions, as well as multi-stage knowledge work such as deep research and analysis reports. Its vision reads charts, diagrams, and tables nested inside files and PDFs, which helps in finance, legal, analytics, and architecture.

On Anthropic's published evaluations it scores 55.8% on Terminal-Bench 4.0, 73.4% on CursorBench 3.2.0, and 65.0% on Humanity's Last Exam with tools, ahead of Claude Opus 5. Pricing is $10 per million input tokens and $50 per million output, with cache reads at $0.25 and Batch API at half price. Cybersecurity and biology requests may be routed to less capable models.

Open Playground ↗Create API Key ↗Getting started →

Updated: Oct 21, 2026

MODEL ID

claude-fable-5-1

Context: 1M
Max output: 128K
Recommended API: messages
Input: text / image / file
Output: text

Providers

3 providers

Compare API prices across providers. Select a provider to view all charges and conditions.

Provider · Pricing details

$10	$50	$0.25
$10	$50	$0.25
$10	$50	$0.25

Reasoning

Default effort: high
Always enabled: Yes
Available effort levels: max / xhigh / high / medium / low

Quick Start

Drop-in code to call this model with Felo API Platform compatible APIs. Start in the Playground when you want to test prompts before writing code.

Open Playground Create API Key

Get your API key

Create a key from your Felo API Platform account and set it as an environment variable.

export FELO_API_KEY="YOUR_API_KEY"

Make your first request

Use this model ID with the Felo API Platform endpoint. Optional request headers such as X-Request-Id can help troubleshooting.

claude-fable-5-1

This model is reasoning-capable. If your selected protocol and model route expose reasoning controls, preserve the returned reasoning metadata when continuing a conversation.

const response = await fetch("https://openapi.felo.ai/api/v1/messages", {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.FELO_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "claude-fable-5-1",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());

Using third-party SDKs

Use compatible SDKs by setting baseURL to https://openapi.felo.ai/api/v1. Use the Anthropic-compatible base URL for Claude-style clients. https://openapi.felo.ai/api.

Enable streaming

Add stream: true to receive responses as server-sent events.

curl -N https://openapi.felo.ai/api/v1/messages \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-fable-5-1",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "stream": true
}'

Endpoint

Felo API Platform exposes compatible model-calling surfaces. Pick the surface your app or agent client already supports.

SurfaceMethodURL

Messages

Anthropic-compatible messages for Claude-style clients.

POST

https://openapi.felo.ai/api/v1/messages

Parameters

NameTypeDefaultDescription

modelstringclaude-fable-5-1Public model ID to call.

max_tokensinteger—Maximum generated tokens.

messagesarray—Conversation messages for Chat Completions.

include_reasoning———

max_completion_tokens———

reasoning———

reasoning_effort———

response_formatobject—Request structured output when supported.

stop———

structured_outputs———

tool_choicestring or object—Controls whether a tool should be called.

toolsarray—Tool calling definitions following compatible schema.

verbosity———

Frequently asked questions

What is Claude Fable 5.1?

Claude Fable 5.1 is Anthropic's fifth-generation flagship, released in September 2026. It shares base weights with the restricted Claude Mythos 5.1 but applies a different safety policy, and it offers a 1M-token context window with up to 128K output tokens. Anthropic positions it for intensive reasoning and long-running autonomous work rather than quick chat. The model is built to keep working unattended for hours or days: planning its own steps, calling tools, recovering when a step fails, and reporting progress. That makes it a fit for feature development across an entire codebase, code review, performance work, and multi-day coding sessions, as well as multi-stage knowledge work such as deep research and analysis reports. Its vision reads charts, diagrams, and tables nested inside files and PDFs, which helps in finance, legal, analytics, and architecture. On Anthropic's published evaluations it scores 55.8% on Terminal-Bench 4.0, 73.4% on CursorBench 3.2.0, and 65.0% on Humanity's Last Exam with tools, ahead of Claude Opus 5. Pricing is $10 per million input tokens and $50 per million output, with cache reads at $0.25 and Batch API at half price. Cybersecurity and biology requests may be routed to less capable models.

How is usage billed?

Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.

Related models

Claude Haiku 5.5

Anthropicclaude-haiku-5-5

Anthropic's cheapest and fastest small model, built for high-volume summarization, classification, and narrow sub-agent work with adjustable reasoning effort.

SummarizationClassificationSub-agent tasksRealtime support

Context

Max output

128K

Input tokens · Base rate

$0.1 / 1M tokens

Output tokens · Base rate

$0.5 / 1M tokens

Claude Opus 5.5

Anthropicclaude-opus-5-5

Anthropic's flagship Claude 5.5 model: a 1M-token context, always-on adaptive thinking, and Opus 5-class agentic performance at roughly 40% lower running cost.

Agentic codingLarge codebasesLong-horizon researchFinancial document review

Context

Max output

128K

Input tokens

$4 / 1M tokens

Output tokens

$20 / 1M tokens

Claude Sonnet 5.5

Anthropicclaude-sonnet-5-5

Anthropic's mid-tier Claude 5.5 model for everyday coding, documents, and agentic terminal work at Sonnet pricing.

Agentic terminal codingBug fixingOffice documentsSlides and spreadsheets

Context

Max output

128K

Input tokens

$2 / 1M tokens

Output tokens

$10 / 1M tokens