NOUMENOpen app
NOUMEN

Anthropic · Frontier

Claude Fable 5

Added Jun 9, 2026

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Anthropic Claude Fable 5 for long-running coding, research, and knowledge-work tasks. Anthropic retains prompts and outputs for 30 days under its Covered Models policy; Zero Data Retention is not available.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • PDF input
Input
Text, Images
Output
Text
Reasoning effort
low · medium · high · xhigh · max
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$10.00
Output
$50.00
Cache read
$1.00
Cache write
$12.50
$20.00 for a 1-hour cache

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
128K
Average output (7 days)
1.2K tokens
Longer than 78% of 465 models

Side by side

Claude Fable 5 compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Claude Fable 5AnthropicThis modelGPT Astra LatestOpenAIRemove
ProviderAnthropicOpenAI
Discovery tierFrontierFrontier
AddedJun 9, 2026Sep 11, 2026
Limits
Context window1M1.05MBest
Max output128K128K
Average output1.2K tokens599 tokens
Pricing, USD per 1M tokens
Input$10.00$10.00
Output$50.00$50.00
Cache read$1.00$1.00
Cache write$12.50$12.50
Performance
Throughput79.4 tok/s171.0 tok/sBest
Time to first token6.0 sBest22.9 s
Request success (24h)100.0%Best97.7%
Benchmark indexes
Intelligence Index49.649.6
Coding Index76.576.7Best
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesYes
Reasoning effortlow, medium, high, xhigh, maxlow, medium, high, xhigh, max

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Claude Fable 5
  • GPT Astra Latest

Intelligence Index

  • Claude Fable 549.6
  • GPT Astra Latest49.6

Claude Fable 5 tested at max reasoning effort

Claude Fable 5: Better than 96% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Claude Fable 5: 76.5
    • GPT Astra Latest: 76.7Top

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Claude Fable 5: 54.1%
    • GPT Astra Latest: 64.6%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Claude Fable 5: 24.7%
    • GPT Astra Latest: 33.6%Top

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Claude Fable 5: 1,537 EloTop
    • GPT Astra Latest: 1,460 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Claude Fable 5: 1,610 EloTop
    • GPT Astra Latest: 1,487 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Claude Fable 5: 24.0%
    • GPT Astra Latest: 30.4%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • Claude Fable 5: 82.3%Top
    • GPT Astra Latest: 79.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • Claude Fable 5: 20.6%
    • GPT Astra Latest: 38.3%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Claude Fable 5: 55.5%Top
    • GPT Astra Latest: 52.7%

  • GPQA Diamond

    Graduate-level science questions

    • Claude Fable 5: 92.6%
    • GPT Astra Latest: 93.9%Top

  • IFBench

    Following precise output instructions

    • Claude Fable 5: 63.5%
    • GPT Astra Latest: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Claude Fable 5: 42.4%
    • GPT Astra Latest: 49.5%Top

  • SciCode

    Scientific computing in Python

    • Claude Fable 5: 61.0%Top
    • GPT Astra Latest: 54.2%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Claude Fable 5: 62.9%
    • GPT Astra Latest: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Claude Fable 5: 98.5%
    • GPT Astra Latest: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Claude Fable 5: 82.3%Top
    • GPT Astra Latest: 79.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Claude Fable 5 was tested at max reasoning effort; compare scores measured at the same effort.Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
79.4 tok/s
Faster than 52% of 250 models
Time to first token
6.0 s
Quicker than 26% of 250 models
Prompt cache hits
36.6%
About $6.70 per 1M input tokens with caching
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 100.0%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-fable-5",
    "reasoning_effort": "medium",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="anthropic/claude-fable-5",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Anthropic

Other Anthropic models, starting with the same family.