CrossModel
Claude Fable 5
anthropic/claude-fable-5
Back to model catalog

Anthropic · Model guide

Claude Fable 5

Compare
anthropic/claude-fable-5

Anthropic's most capable generally available model, built for demanding reasoning and long-running agent work. Thinking is always on here: requests that try to disable it are rejected, so effort is the only dial. Claude Mythos 5 is the same underlying model with some safeguards lifted, and is invitation-only.

Modalities
TextImageText
Context
1M
Max output
128K
Price / 1M tokens
$ 10.00in$ 50.00out
StreamingTool callingJSON outputImage inputThinking mode

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorNext-generation intelligence for long-running agents.source

Best for

  • Agentic coding · Anthropic positions it for long-running agents.(vendor claim)source

  • Professional knowledge work · Anthropic calls it state of the art on nearly all benchmarks it tested, including knowledge work and vision.(vendor claim)source

Neighbouring models
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 10.00
Output$ 50.00
Cache read$ 1.00
Cache write$ 12.50
Estimate a request
$ 0.2000
Estimated cost per request
10.0K × $ 10.00
+ 2.0K × $ 50.00
≈ $ 200.00 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
1.0M tokens
Max output
128.0K tokens
Input / output modalities
Text + Image → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· always on
Reasoning effort
low · medium · high · xhigh · max
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specsplatform.claude.comCapabilitiesplatform.claude.com 1platform.claude.com 2platform.claude.com 3platform.claude.com 4

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding
  • Frontier-Bench v0.1
    score·Anthropic · 2026-07-24setup not fully disclosed
    33.7%
Agentic search
  • BrowseComp (with tools)
    accuracy·Anthropic · 2026-07-24setup not fully disclosed
    87.4%
Agentic work
  • AutomationBench
    score·Anthropic · 2026-06-09setup not fully disclosed

    Anthropic publishes a single Claude Mythos 5 / Claude Fable 5 column showing the higher of the two; the table's methodology note puts the pair within 1-3 percentage points on rows not marked with an asterisk, and this row is not marked.

    17.4%
Coding
  • SWE-Bench Pro
    resolved_rate·Anthropic · 2026-06-09setup not fully disclosed

    Anthropic publishes a single Claude Mythos 5 / Claude Fable 5 column showing the higher of the two; the table's methodology note puts the pair within 1-3 percentage points on rows not marked with an asterisk, and this row is not marked.

    80.3%
Computer use
  • OSWorld 2.0
    success_rate·Anthropic · 2026-07-24setup not fully disclosed
    66.1%
  • OSWorld-Verified
    success_rate·Anthropic · 2026-06-09setup not fully disclosed

    Anthropic publishes a single Claude Mythos 5 / Claude Fable 5 column showing the higher of the two; the table's methodology note puts the pair within 1-3 percentage points on rows not marked with an asterisk, and this row is not marked.

    85%
Knowledge work
  • GDPval-AA
    elo·Anthropic · 2026-06-09setup not fully disclosed

    Anthropic publishes a single Claude Mythos 5 / Claude Fable 5 column showing the higher of the two; the table's methodology note puts the pair within 1-3 percentage points on rows not marked with an asterisk, and this row is not marked.

    1932
Reasoning
  • Humanity's Last Exam
    accuracy·Anthropic · 2026-07-24setup not fully disclosed

    No tools.

    56.5%
  • Humanity's Last Exam (with tools)
    accuracy·Anthropic · 2026-07-24setup not fully disclosed

    Anthropic does not disclose which tools the run had.

    63.9%
Spatial reasoning
  • Blueprint-Bench 2
    score·Anthropic · 2026-06-09setup not fully disclosed

    Anthropic publishes a single Claude Mythos 5 / Claude Fable 5 column showing the higher of the two; the table's methodology note puts the pair within 1-3 percentage points on rows not marked with an asterisk, and this row is not marked.

    38.6%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is Claude Fable 5?
Claude Fable 5 is available on CrossModel as anthropic/claude-fable-5. It has a 1M-token context window and can return up to 128K tokens per request.
How much does Claude Fable 5 cost?
Currently $ 10.00 per 1M input tokens and $ 50.00 per 1M output tokens. Cached input is billed at $ 1.00 per 1M.
Does Claude Fable 5 support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.