Enterprise DNAEnterprise DNA
LModelsBest vision
Anthropic logo

Claude Fable 5.1

by Anthropic

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, fro

Visit AnthropicSubmit your build →
CF

Models

Claude Fable 5.1

Added 3 Sept 2026

#anthropic

Overview

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...

Best for

Best for
Long-running planning and code review

How to use / API access

Call via OpenRouter with model id `anthropic/claude-fable-5.1`.

  • openrouter · anthropic/claude-fable-5.1 Docs

OpenRouter id: anthropic/claude-fable-5.1

Benchmarks

  • Intelligence Index (artificial-analysis): 53.4 index
  • Coding Index (artificial-analysis): 81.6 index
  • Agentic Index (artificial-analysis): 57.9 index
  • Design Arena fullstack (other): 1326 elo · #1
  • Design Arena godotgamedev (other): 1327 elo · #1
  • Design Arena mobileapps (other): 1265 elo · #3
  • Design Arena python-pptxslides (other): 1328 elo · #1

Notes

Claude Fable 5.1 is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Planning a multi-step change with checkpoints
  • text, image, file input; text output on the listed OpenRouter route

Cons

  • Using a premium model before measuring simpler alternatives
  • Treating a long answer as proof the work was executed
  • Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →

USAGE / OPENROUTER

How much Claude Fable 5.1 is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
290B ▼15.5%
Requests, last 7 days
2.4M
Tool calls, last 7 days
1.5M
Intelligence score
53.4
People's vote
1512
Average cost per request
$24.44
Price per million tokens
$10 in · $50 out
0100B200B19 Sept: 64.7B tokens, 469K requests20 Sept: 57.3B tokens, 508K requests21 Sept: 78.4B tokens, 632K requests22 Sept: 77.5B tokens, 643K requests23 Sept: 55.2B tokens, 540K requests24 Sept: 107B tokens, 900K requests25 Sept: 169B tokens, 1.2M requests26 Sept: 81.9B tokens, 789K requests27 Sept: 49.2B tokens, 372K requests28 Sept: 76.6B tokens, 660K requests29 Sept: 71.3B tokens, 817K requests30 Sept: 66.8B tokens, 656K requests1 Oct: 63.6B tokens, 582K requests2 Oct: 37.1B tokens, 372K requests3 Oct: 26.2B tokens, 240K requests4 Oct: 28.1B tokens, 277K requests5 Oct: 33.1B tokens, 364K requests6 Oct: 40.4B tokens, 435K requests7 Oct: 53.7B tokens, 430K requests8 Oct: 47.6B tokens, 384K requests9 Oct: 53.4B tokens, 396K requests10 Oct: 42.2B tokens, 302K requests11 Oct: 72.8B tokens, 353K requests12 Oct: 42.1B tokens, 339K requests13 Oct: 48.1B tokens, 388K requests14 Oct: 41.8B tokens, 335K requests15 Oct: 58.6B tokens, 438K requests16 Oct: 36B tokens, 356K requests17 Oct: 33.2B tokens, 284K requests18 Oct: 30.1B tokens, 274K requests19 Sept3 Oct17 Oct18 OctSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Claude Fable 5.1.

Specifications reviewed; no EDNA task evaluation has been run. Sources checked 2026-10-20. Hosting routes and app features can differ.

DeveloperAnthropic
Exact model identifieranthropic/claude-fable-5.1
Inputtext, image, file
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient

Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.

Consider it for

  • Planning a multi-step change with checkpoints
  • Reviewing a large implementation against a design

Watch for

  • Using a premium model before measuring simpler alternatives
  • Treating a long answer as proof the work was executed

PRACTICAL EXERCISE / NOT RUN BY ENTERPRISE DNA

Try the model on a small, checkable task.

Plan a migration from a single currency ledger to per-invoice currency. Identify schema, API, reports and rollback work; list dependencies and stop before running changes.

Check the result: The plan separates historical invoices from new ones and includes reconciliation and rollback checks.

Compare another approach

anthropic claude sonnet 5 5 ↗openai gpt 6 1 sol ↗
Inspect the sources and their scope
provider source ↗

Developer documentation for model family or task. OpenRouter route-specific properties remain catalogue claims; EDNA has not executed a task evaluation.

Checked 2026-10-19
catalogue source ↗

anthropic/claude-fable-5.1: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-10-20
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Write a clear business documentWorkflow & starter prompt ↗Analyse a spreadsheetWorkflow & starter prompt ↗Research a companyWorkflow & starter prompt ↗Build an appWorkflow & starter prompt ↗Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

Check the source

Price date: 2026-10-20. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 53.4 (2026-10-18) ↗Coding Index: 81.6 (2026-10-18) ↗Agentic Index: 57.9 (2026-10-18) ↗
Compare this model with alternatives →