Anthropic: Claude Fable 5

Claude model for creative writing, analysis, and controlled agent workflows

claude-fable-5

AvailableAnthropicChatCached input 90% less

Input / Output-70%: $10.00 / $50.00$3.00 / $15.00
Context: 1M
Released: Jun 9, 2026
Max output: 128K
Modalities: VisionChat
Capabilities: Tool usePrompt CacheReasoning

About Claude Fable 5

Claude Fable 5 is Anthropic's general-release model from the Mythos-class tier, launched in June 2026 above the Opus line. It targets software engineering, knowledge work, vision, and scientific research. Fable 5 is the same model as Mythos 5 with safety classifiers added, and Anthropic has since superseded it with Fable 5.1.

Where it works well

Anthropic describes it as leading on nearly all tested benchmarks, with software engineering and knowledge work singled out.
Stripe reported in Anthropic's launch post that it finished a 50-million-line codebase migration in a day instead of two months.
Vision is a highlight: Anthropic cites rebuilding web applications from screenshots alone.
Adaptive thinking is always on, so the model chooses how long to reason and you steer it with effort.

When to choose another model

Safety classifiers can decline cybersecurity and some biology or chemistry requests, with those falling back to Opus 4.8.
It is slower than the Opus and Sonnet models, so it is a poor fit for chat that needs instant replies.
Anthropic lists it as legacy, and Fable 5.1 improves on it and is the version to choose for new work.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to textMessages API

POST/v1/messages

API format:

curl https://api.tokenlab.sh/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-xxx" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-fable-5",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Default spec

per 1M tokens

Official price: Input $10.00 / Output $50.00 / Cache read $1.00 / Cache write $12.50
Verified price: Input $3.00 / Output $15.00 / Cache read $0.30 / Cache write $3.75
Discount: -70%

Prompt cache pricing

Cache read

Official price: $1.00
Verified price: $0.30
Discount: -70%

Cache write

Official price: $12.50
Verified price: $3.75
Discount: -70%

Tool fees

Charged per call, only when the model uses the tool.

Web search

Official price: $0.01/search
Verified price: $0.003/search
Discount: -70%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Default spec	Input $10.00 / Output $50.00 / Cache read $1.00 / Cache write $12.50	Input $3.00 / Output $15.00 / Cache read $0.30 / Cache write $3.75	-70%
Prompt cache pricing
Cache read	$1.00	$0.30	-70%
Cache write	$12.50	$3.75	-70%
Tool feesCharged per call, only when the model uses the tool.
Web search	$0.01/search	$0.003/search	-70%

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 10, 2026, 06:16 PM UTC

7-day median latency: 5.2 sn=52

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Claude Fable 5 in Console with a prompt ready to edit or send.

Help me try claude-fable-5 with a short message at /v1/messages. Show the reply, latency, and cost.

Use cases

Best for

Reasoning
Vision

Large-scale code migrations
Point it at a big codebase and a migration plan, and let it do the repetitive transformation and test repair across thousands of files.
Financial and legal analysis
Hand it long filings or agreements for senior-level reasoning, with citations to the passages it relied on.
Screenshot to application
Give it screenshots of an existing web app and ask for a working front end that reproduces layout and behavior.

Prompt examples

Below is a screenshot of our admin dashboard. Rebuild it as a React component set with the same layout and states.

Migrate this repository from the old logging library to the new one, update call sites, and report anything you were unable to convert safely.

Read these three 10-K filings and explain why gross margin moved between years, citing the sections.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is the difference between Claude Fable 5 and Mythos 5?

They are the same model with different safeguards. Fable 5 has classifiers that block cybersecurity exploitation and some biology and distillation requests, and Mythos 5 is offered by invitation for vetted defensive security work through Project Glasswing.

What happens when Fable 5 declines a request?

A safeguard classifier stops the response and, per Anthropic, many biology queries fall back to Claude Opus 4.8. The safeguards are tuned to be cautious, so some harmless requests are caught.

Is Claude Fable 5 the newest Fable?

No. Fable 5.1 followed in September 2026 with higher benchmark scores and fewer false positives from the safeguards. Anthropic lists Fable 5 as legacy and publishes a migration guide to 5.1.

Can Claude Fable 5 take image input?

Yes. It accepts text and images and writes text. Anthropic highlights vision, including reconstructing web applications from screenshots. It does not generate images or audio.

How much does Claude Fable 5 cost?

On TokenLab, Claude Fable 5 costs Input $3.00 / Output $15.00 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What are the context window and output limit of Claude Fable 5?

Claude Fable 5 accepts up to 1,000,000 tokens of context and returns up to 128,000 tokens in one response.

Which endpoint should Claude Fable 5 use?

Use https://api.tokenlab.sh/v1/messages for Claude Fable 5. The request example below shows the matching code shape.

Which operations does Claude Fable 5 support?

Claude Fable 5 supports Text to text. Select an operation above to see its endpoint and request example.