Claude Fable 5

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.

It is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.

anthropic/claude-fable-5
Organization
Anthropic
Providers
38
Context
1,000,000
Output limit
128,000
Knowledge
2026-01-31
Release
2026-06-09
Updated
2026-06-09
Weights
Closed
Input
text, image, pdf
Output
text
Capabilities
Tools, Reasoning

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

49 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
302.AI
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
Abacus
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
AIHubMix
claude-fable-5
1,000,000128,000$11.00 / $55.00YesYesYes
View
Amazon Bedrock
anthropic.claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
Amazon Bedrock
global.anthropic.claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
Amazon Bedrock
eu.anthropic.claude-fable-5
1,000,000128,000$11.00 / $55.00YesYes—
View
Amazon Bedrock
us.anthropic.claude-fable-5
1,000,000128,000$11.00 / $55.00YesYes—
View
Azure
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
Azure Cognitive Services
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
Cloudflare AI Gateway
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
CrossModel
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
DevPass (LLM Gateway)
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
Eden AI
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
FreeModel
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
GitHub Copilot
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
GitLab Duo
duo-chat-fable-5
1,000,000128,000$0.00 / $0.00YesYes—
View
Impossibl
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
Kenari
claude-fable-5
1,000,000128,000$0.00 / $0.00YesYes—
View
Kilo Gateway
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
LLM Gateway
aws-bedrock/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesNo
View
LLM Gateway
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
LLM Gateway
azure-anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
Merge Gateway
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
Modelis
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
Model Oracle AI
claude-fable-5
1,000,000128,000— / —YesYes—
View
NanoGPT
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
Neon
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
Ofox
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
OpenCode Zen
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
Amazon Bedrockvia OpenRouter
anthropic/claude-fable-5
unknown
1,000,000128,000$10.00 / $50.00YesYesNo
View
Anthropicvia OpenRouter
anthropic/claude-fable-5
unknown
1,000,000128,000$10.00 / $50.00YesYesYes
View
Azurevia OpenRouter
anthropic/claude-fable-5
unknown
1,000,000128,000$10.00 / $50.00YesYesYes
View
Claude Platform on AWSvia OpenRouter
anthropic/claude-fable-5
unknown
1,000,000128,000$10.00 / $50.00YesYesYes
View
Googlevia OpenRouter
anthropic/claude-fable-5
unknown
1,000,000128,000$11.00 / $55.00YesYesYes
View
Googlevia OpenRouter
anthropic/claude-fable-5
unknown
1,000,000128,000$10.00 / $50.00YesYesYes
View
Opper
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
OrcaRouter
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
Pioneer
claude-fable-5
1,000,000128,000$11.00 / $55.00YesYes—
View
Requesty
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
Requesty
claude-fable-5@eu
1,000,000128,000$11.00 / $55.00YesYesYes
View
Snowflake Cortex
claude-fable-5
1,000,000128,000— / —YesYes—
View
Tempr Gateway
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
Venice AI
claude-fable-5
1,000,000128,000$12.00 / $60.00YesYesYes
View
Vercel AI Gateway
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View
Vertex
claude-fable-5@default
1,000,000128,000$10.00 / $50.00YesYes—
View
Vertex (Anthropic)
claude-fable-5@default
1,000,000128,000$10.00 / $50.00YesYes—
View
Vivgrid
claude-fable-5
1,000,000128,000$10.00 / $50.00YesYesYes
View
Xpersona
claude-fable-5
1,000,000128,000$3.00 / $18.50YesYes—
View
ZenMux
anthropic/claude-fable-5
1,000,000128,000$10.00 / $50.00YesYes—
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.00Per 1M input tokens
Output from$0.00Per 1M output tokens
Available offers49Across 38 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 6 lowest-priced configurations
InputOutput
Amazon Bedrockamazon-bedrock
$10.00$50.00
Anthropicanthropic
$10.00$50.00
Azureazure
$10.00$50.00
Claude Platform on AWSclaude-on-aws
$10.00$50.00
Googlegoogle-vertex/global
$10.00$50.00
Googlegoogle-vertex/europe
$11.00$55.00
anthropic/claude-fable-5Observed
Input
$10.00
Output
$50.00
Cache read
$1.00
Cache write
$12.50
Cache write · 1 hour
$20.00
Additional fees and pricing conditions
web search
$0.01 / search
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Amazon Bedrockamazon-bedrock$10.00$50.00$1.00$12.50
Anthropicanthropic$10.00$50.00$1.00$12.50
Azureazure$10.00$50.00$1.00$12.50
Claude Platform on AWSclaude-on-aws$10.00$50.00$1.00$12.50
Googlegoogle-vertex/europe$11.00$55.00$1.10$13.75
Googlegoogle-vertex/global$10.00$50.00$1.00$12.50

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 5 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock
4,271.5–8,449.22 ms
Anthropicanthropic
3,033–11,282.61 ms
Azureazure
4,852.5–5,222.09 ms
Claude Platform on AWSclaude-on-aws
5,323–26,305.04 ms
Googlegoogle-vertex/global
3,713.5–4,320.8 ms
All latency percentiles 5 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock4,271.5 ms6,249.25 ms7,447.7 ms8,449.22 ms
Anthropicanthropic3,033 ms4,604.5 ms5,489.3 ms11,282.61 ms
Azureazure4,852.5 ms5,152.25 ms5,195.9 ms5,222.09 ms
Claude Platform on AWSclaude-on-aws5,323 ms5,485 ms5,802.2 ms26,305.04 ms
Googlegoogle-vertex/global3,713.5 ms3,947.75 ms4,256 ms4,320.8 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 5 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock
40–56.62 t/s
Anthropicanthropic
50–100.26 t/s
Azureazure
61–66.82 t/s
Claude Platform on AWSclaude-on-aws
59–63.88 t/s
Googlegoogle-vertex/global
52–63.37 t/s
All throughput percentiles 5 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock40 t/s43.25 t/s54.1 t/s56.62 t/s
Anthropicanthropic50 t/s67 t/s77 t/s100.26 t/s
Azureazure61 t/s62.5 t/s65.2 t/s66.82 t/s
Claude Platform on AWSclaude-on-aws59 t/s61 t/s63 t/s63.88 t/s
Googlegoogle-vertex/global52 t/s55.75 t/s57.7 t/s63.37 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 6 endpoints
Endpoint5 minutes30 minutes24 hours
Amazon Bedrockamazon-bedrock
Anthropicanthropic
Azureazure
Claude Platform on AWSclaude-on-aws
Googlegoogle-vertex/europe
Googlegoogle-vertex/global

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations
anthropic/claude-fable-5Observed
Benchmark profileArtificial Analysis · shared source scale from 0 to 80
Coding76.5
Agentic50.7
Intelligence49.6
Design ArenaCategoryEloWin rateRank
agentsagenticgamedev1,28561.9%1
agentsagentichtmlslides1,25459.4%1
agentsagenticslides(html)1,25259.5%1
agentsandroidnative1,29765.1%2
agentsfullstack1,27858.2%6
agentsgodotgamedev1,29264.3%2
agentshtmlslides1,27763.1%1
agentsmobileapps1,25960.5%5
agentspython-pptxslides1,29561.4%3
agentswebapps1,25456.4%8
models3d1,33461.8%10
modelsasciiart1,33868%2
modelscodecategories1,31757.7%9
modelsdataviz1,31457.5%10
modelsgamedev1,34960.9%6
modelssvg1,30162.6%5
modelsuicomponent1,32558.1%10
modelswebsite1,30256%12

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
gpqa diamondAnthropic: Claude Fable 5
85.455%
tau bench verified airlineAnthropic: Claude Fable 5
79.852%
EvaluationConfigurationSourceResultsDetails
models · websiteClaude Fable 5anthropic/claude-5-fable-20260609Design Arena1,302 Elo
Details
gpqa diamondAnthropic: Claude Fable 5anthropic/claude-5-fable-20260609OpenRouter85.455%
Details
models · asciiartClaude Fable 5anthropic/claude-5-fable-20260609Design Arena1,338 Elo
Details
models · 3dClaude Fable 5anthropic/claude-5-fable-20260609Design Arena1,334 Elo
Details
models · svgClaude Fable 5anthropic/claude-5-fable-20260609Design Arena1,301 Elo
Details
tau bench verified airlineAnthropic: Claude Fable 5anthropic/claude-5-fable-20260609OpenRouter79.852%
Details
Composite indicesClaude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)anthropic/claude-5-fable-20260609Artificial AnalysisIntelligence 49.6 · Coding 76.5 · Agentic 50.7
Details
models · datavizClaude Fable 5anthropic/claude-5-fable-20260609Design Arena1,314 Elo
Details
models · uicomponentClaude Fable 5anthropic/claude-5-fable-20260609Design Arena1,325 Elo
Details
models · gamedevClaude Fable 5anthropic/claude-5-fable-20260609Design Arena1,349 Elo
Details
models · codecategoriesClaude Fable 5anthropic/claude-5-fable-20260609Design Arena1,317 Elo
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Claude Codeanthropic/claude-5-fable-2026060950+ turns
$26.19213
Details
Claude Codeanthropic/claude-5-fable-202606091 turn
$0.289272
Details
Claude Codeanthropic/claude-5-fable-202606092–9 turns
$1.048723
Details
Hermes Agentanthropic/claude-5-fable-202606092–9 turns
$0.727619
Details
Hermes Agentanthropic/claude-5-fable-2026060950+ turns
$21.746696
Details
Claude Codeanthropic/claude-5-fable-2026060910–49 turns
$4.526512
Details
Hermes Agentanthropic/claude-5-fable-202606091 turn
$0.031873
Details
Hermes Agentanthropic/claude-5-fable-2026060910–49 turns
$4.015211
Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days
Daily token usage2,397,450,895,511 reported tokens · 56 days with observations
Jul 6, 2026Oct 3, 2026
Daily observations · 56 days
Date (UTC)Reported tokensReported routes
Sep 14, 202640,748,883,2121
Sep 1, 202637,242,219,0971
Aug 31, 202637,104,844,9491
Aug 28, 202633,553,366,1441
Aug 27, 202638,942,806,0781
Aug 26, 202637,977,154,9131
Aug 25, 202640,123,386,3151
Aug 24, 202633,415,623,2241
Aug 23, 202622,522,875,1141
Aug 22, 202626,615,977,2441
Aug 21, 202638,767,734,2481
Aug 20, 202647,031,536,7871
Aug 19, 202644,738,863,8671
Aug 18, 202643,052,485,6621
Aug 17, 202647,550,444,9931
Aug 16, 202630,345,083,5081
Aug 15, 202632,553,972,6181
Aug 14, 202634,536,732,8061
Aug 13, 202647,151,354,4781
Aug 12, 202649,352,997,3851
Aug 11, 202641,321,247,6411
Aug 10, 202634,621,678,3511
Aug 9, 202621,309,456,0461
Aug 8, 202630,467,132,6491
Aug 7, 202630,513,079,9171
Aug 6, 202630,738,585,0571
Aug 5, 202639,691,950,4781
Aug 4, 202638,851,050,4761
Aug 3, 202635,265,680,4061
Aug 2, 202623,607,616,2031
Aug 1, 202621,846,491,5611
Jul 31, 202635,280,739,3151
Jul 30, 202631,620,928,5921
Jul 29, 202637,210,310,0131
Jul 28, 202635,467,023,2751
Jul 27, 202633,561,574,3421
Jul 26, 202624,980,786,6061
Jul 25, 202627,857,583,2891
Jul 24, 202652,630,353,7811
Jul 23, 202653,270,182,2021
Jul 22, 202649,942,002,0031
Jul 21, 202651,105,290,6171
Jul 20, 202665,622,659,6481
Jul 19, 202661,665,398,7521
Jul 18, 202659,942,344,4241
Jul 17, 202681,911,847,0921
Jul 16, 202661,276,263,3411
Jul 15, 202668,420,531,8871
Jul 14, 202672,066,317,0521
Jul 13, 202665,208,173,1311
Jul 12, 202629,940,202,5931
Jul 11, 202629,236,732,7951
Jul 10, 202649,137,187,9331
Jul 9, 202661,327,813,0421
Jul 8, 202672,566,913,9401
Jul 7, 202674,639,424,4191

Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
anthropic/claude-fable-5Observed
Context
1,000,000
Maximum output
128,000
Tokenizer
Claude
Input
text, image, file
Output
text
Moderation
Yes
Added to OpenRouter
2026-06-09
Base URLhttps://openrouter.ai/api/v1
Model IDanthropic/claude-fable-5
Version IDanthropic/claude-5-fable-20260609

Reasoning

Required
Yes
Enabled by default
Not reported
Default effort
high
Supported efforts
max, xhigh, high, medium, low

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • reasoning_effort
  • response_format
  • stop
  • structured_outputs
  • tool_choice
  • tools
  • verbosity

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Claude Fable 5 cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Claude Fable 5?

There are 49 cataloged offers across 38 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,000,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · b4368b89eb97
  • · 7949123b2808