Claude Fable 5.1

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 code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.

anthropic/claude-fable-5-1

Organization: Anthropic
Family: claude-fable
Providers: 37
Context: 1,000,000
Output limit: 128,000
Knowledge: 2026-06
Release: 2026-09-01
Updated: —
Weights: Closed
Input: text, image/jpeg, image/png, image/gif, image/webp, application/pdf
Output: text
Capabilities: —

Providers

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

46 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
AIHubMix	claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
AI/ML API	anthropic/claude-fable-5.1	1,000,000	128,000	— / —	—	—	—	View
Aixy	anthropic/claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Amazon Bedrock	global.anthropic.claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Amazon Bedrock	us.anthropic.claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Amazon Bedrock	anthropic.claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Anthropic	claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Azure	claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Boundless	claude-fable-5.1	262,144	128,000	— / —	—	—	—	View
Cloudflare AI Gateway	anthropic/claude-fable-5.1	1,000,000	128,000	— / —	—	—	—	View
CommandCode	claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
CrossModel	anthropic/claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
DevPass (LLM Gateway)	claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
DigitalOcean	anthropic-claude-fable-5.1	1,000,000	128,000	— / —	—	—	—	View
Eden AI	anthropic/claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Eden AI	anthropic/claude-fable-latest	1,000,000	128,000	— / —	—	—	—	View
GitHub Copilot	claude-fable-5.1	1,000,000	128,000	— / —	—	—	—	View
GitLab Duo	duo-chat-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Kilo Gateway	anthropic/claude-fable-5.1	1,000,000	128,000	— / —	—	—	—	View
LLM Gateway	aws-bedrock/claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
LLM Gateway	azure-anthropic/claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
LLM Gateway	anthropic/claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Merge Gateway	anthropic/claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
NanoGPT	anthropic/claude-fable-5.1	1,000,000	128,000	— / —	—	—	—	View
NEAR AI Cloud	anthropic/claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Neon	claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Ofox	anthropic/claude-fable-5.1	1,000,000	128,000	— / —	—	—	—	View
OpenCode	claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Amazon Bedrockvia OpenRouter	anthropic/claude-fable-5.1 unknown	1,000,000	128,000	$10.00 / $50.00	Yes	Yes	No	View
Anthropicvia OpenRouter	anthropic/claude-fable-5.1 unknown	1,000,000	128,000	$10.00 / $50.00	Yes	Yes	Yes	View
Azurevia OpenRouter	anthropic/claude-fable-5.1 unknown	1,000,000	128,000	$10.00 / $50.00	Yes	Yes	Yes	View
Googlevia OpenRouter	anthropic/claude-fable-5.1 unknown	1,000,000	128,000	$10.00 / $50.00	Yes	Yes	Yes	View
Opper	claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Perplexity Agent	anthropic/claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Prime Inference	anthropic/claude-fable-5.1	1,000,000	128,000	— / —	—	—	—	View
Requesty	claude-fable-5.1	1,000,000	128,000	— / —	—	—	—	View
Requesty	claude-fable-5.1@eu	1,000,000	128,000	— / —	—	—	—	View
Standard Compute	anthropic/claude-fable-5.1	1,000,000	50,000	— / —	—	—	—	View
Tempr Gateway	anthropic/claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Venice AI	claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
Vercel AI Gateway	anthropic/claude-fable-5.1	1,000,000	128,000	— / —	—	—	—	View
Vertex	claude-fable-5-1@default	1,000,000	128,000	— / —	—	—	—	View
Vertex (Anthropic)	claude-fable-5-1@default	1,000,000	128,000	— / —	—	—	—	View
Vivgrid	claude-fable-5-1	1,000,000	128,000	— / —	—	—	—	View
ZenMux	anthropic/claude-fable-5.1	1,000,000	128,000	— / —	—	—	—	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$10.00Per 1M input tokens

Output from$50.00Per 1M output tokens

Available offers46Across 37 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 · 4 lowest-priced configurations

InputOutput

Amazon Bedrockamazon-bedrock

$10.00$50.00

Anthropicanthropic

$10.00$50.00

Azureazure

$10.00$50.00

Googlegoogle-vertex/global

$10.00$50.00

anthropic/claude-fable-5.1Observed Oct 10, 2026, 11:31 AM UTC

Input: $10.00
Output: $50.00
Cache read: $0.25
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

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Amazon Bedrockamazon-bedrock	$10.00	$50.00	$0.25	$12.50
Anthropicanthropic	$10.00	$50.00	$0.25	$12.50
Azureazure	$10.00	$50.00	$0.25	$12.50
Googlegoogle-vertex/global	$10.00	$50.00	$0.25	$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 · 3 endpoints

P50P75P90P99

Anthropicanthropic

2,679–14,973.49 ms

Azureazure

2,095.5–8,501.34 ms

Googlegoogle-vertex/global

3,877–22,240.62 ms

All latency percentiles 3 endpoints

Endpoint	P50	P75	P90	P99
Anthropicanthropic	2,679 ms	4,430 ms	5,785 ms	14,973.49 ms
Azureazure	2,095.5 ms	4,470.5 ms	5,633.8 ms	8,501.34 ms
Googlegoogle-vertex/global	3,877 ms	9,899 ms	13,618.7 ms	22,240.62 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 3 endpoints

P50P75P90P99

Anthropicanthropic

66–110 t/s

Azureazure

33–66.7 t/s

Googlegoogle-vertex/global

67.5–114.23 t/s

All throughput percentiles 3 endpoints

Endpoint	P50	P75	P90	P99
Anthropicanthropic	66 t/s	77 t/s	89 t/s	110 t/s
Azureazure	33 t/s	45 t/s	54.5 t/s	66.7 t/s
Googlegoogle-vertex/global	67.5 t/s	79.25 t/s	95 t/s	114.23 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 · 4 endpoints

Endpoint5 minutes30 minutes24 hours

Amazon Bedrockamazon-bedrockObserved Oct 10, 2026, 11:31 AM UTC

—

AnthropicanthropicObserved Oct 10, 2026, 11:31 AM UTC

100%

AzureazureObserved Oct 10, 2026, 11:31 AM UTC

100%

Googlegoogle-vertex/globalObserved Oct 10, 2026, 11:31 AM UTC

—

100%

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-5.1Observed Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 90

Coding

81.6

Agentic

57.9

Intelligence

53.4

Design Arena	Category	Elo	Win rate	Rank
agents	fullstack	1,325	57.2%	1
agents	godotgamedev	1,327	60.7%	1
agents	mobileapps	1,265	56.3%	3
agents	python-pptxslides	1,328	62.6%	1
agents	webapps	1,310	56.1%	1
models	3d	1,398	67.7%	3
models	asciiart	1,329	65%	3
models	codecategories	1,341	59.3%	4
models	dataviz	1,348	61.8%	5
models	gamedev	1,389	65.6%	3
models	svg	1,302	56.4%	6
models	uicomponent	1,342	59.6%	7
models	website	1,318	56.3%	5

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 5.1

89.933%

tau bench verified airlineAnthropic: Claude Fable 5.1

79.167%

Evaluation	Configuration	Source	Results	Details
gpqa diamond	Anthropic: Claude Fable 5.1anthropic/claude-fable-5.1-20260831	OpenRouter	89.933%	Details
models · codecategories	Claude Fable 5.1anthropic/claude-fable-5.1-20260831	Design Arena	1,336 Elo	Details
Composite indices	Claude Fable 5.1 (Max, Default Fallback)anthropic/claude-fable-5.1-20260831	Artificial Analysis	Intelligence 53.4 · Coding 81.6 · Agentic 57.9	Details
models · website	Claude Fable 5.1anthropic/claude-fable-5.1-20260831	Design Arena	1,313 Elo	Details
models · 3d	Claude Fable 5.1anthropic/claude-fable-5.1-20260831	Design Arena	1,393 Elo	Details
models · dataviz	Claude Fable 5.1anthropic/claude-fable-5.1-20260831	Design Arena	1,344 Elo	Details
models · asciiart	Claude Fable 5.1anthropic/claude-fable-5.1-20260831	Design Arena	1,323 Elo	Details
models · svg	Claude Fable 5.1anthropic/claude-fable-5.1-20260831	Design Arena	1,301 Elo	Details
models · gamedev	Claude Fable 5.1anthropic/claude-fable-5.1-20260831	Design Arena	1,383 Elo	Details
tau bench verified airline	Anthropic: Claude Fable 5.1anthropic/claude-fable-5.1-20260831	OpenRouter	79.167%	Details
models · uicomponent	Claude Fable 5.1anthropic/claude-fable-5.1-20260831	Design Arena	1,336 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.

Apps & session costs

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

30-day sample · through Oct 18, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	anthropic/claude-fable-5.1-20260831	1 turn	$0.006881	Details
Claude Code	anthropic/claude-fable-5.1-20260831	1 turn	$0.342393	Details
Claude Code	anthropic/claude-fable-5.1-20260831	2–9 turns	$1.049495	Details
Claude Code	anthropic/claude-fable-5.1-20260831	10–49 turns	$3.733755	Details
Claude Code	anthropic/claude-fable-5.1-20260831	50+ turns	$21.273243	Details
Hermes Agent	anthropic/claude-fable-5.1-20260831	50+ turns	$15.820315	Details
Hermes Agent	anthropic/claude-fable-5.1-20260831	2–9 turns	$0.503654	Details
Hermes Agent	anthropic/claude-fable-5.1-20260831	10–49 turns	$3.359274	Details

Source: OpenRouter, as of Oct 20, 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 usage2,331,120,585,681 reported tokens · 34 days with observations

169B0

2026-09-02
67,837,314,055 tokens

2026-09-03
74,829,968,678 tokens

2026-09-04
70,704,483,461 tokens

2026-09-05
40,127,893,080 tokens

2026-09-06
41,196,636,949 tokens

2026-09-07
45,809,813,103 tokens

2026-09-08
55,412,654,953 tokens

2026-09-09
53,377,229,975 tokens

2026-09-10
61,445,647,589 tokens

2026-09-11
61,154,457,835 tokens

2026-09-12
48,637,635,954 tokens

2026-09-13
55,872,948,637 tokens

2026-09-14
72,604,668,609 tokens

2026-09-15
70,249,790,343 tokens

2026-09-16
73,132,223,593 tokens

2026-09-17
78,111,886,659 tokens

2026-09-18
70,916,765,820 tokens

2026-09-19
64,655,055,740 tokens

2026-09-20
57,241,636,095 tokens

2026-09-21
78,352,038,278 tokens

2026-09-22
77,505,875,010 tokens

2026-09-23
54,976,508,979 tokens

2026-09-24
107,077,593,879 tokens

2026-09-25
168,902,357,616 tokens

2026-09-26
81,895,060,158 tokens

2026-09-27
49,180,620,194 tokens

2026-09-28
76,570,758,975 tokens

2026-09-29
71,299,644,588 tokens

2026-09-30
66,781,829,482 tokens

2026-10-01
63,623,655,477 tokens

2026-10-07
53,696,704,671 tokens

2026-10-11
72,766,600,105 tokens

2026-10-15
58,617,530,483 tokens

2026-10-23
86,555,096,658 tokens

Jul 26, 2026Oct 23, 2026

Daily observations · 34 days

Date (UTC)	Reported tokens	Reported routes
Oct 23, 2026	86,555,096,658	1
Oct 15, 2026	58,617,530,483	1
Oct 11, 2026	72,766,600,105	1
Oct 7, 2026	53,696,704,671	1
Oct 1, 2026	63,623,655,477	1
Sep 30, 2026	66,781,829,482	1
Sep 29, 2026	71,299,644,588	1
Sep 28, 2026	76,570,758,975	1
Sep 27, 2026	49,180,620,194	1
Sep 26, 2026	81,895,060,158	1
Sep 25, 2026	168,902,357,616	1
Sep 24, 2026	107,077,593,879	1
Sep 23, 2026	54,976,508,979	1
Sep 22, 2026	77,505,875,010	1
Sep 21, 2026	78,352,038,278	1
Sep 20, 2026	57,241,636,095	1
Sep 19, 2026	64,655,055,740	1
Sep 18, 2026	70,916,765,820	1
Sep 17, 2026	78,111,886,659	1
Sep 16, 2026	73,132,223,593	1
Sep 15, 2026	70,249,790,343	1
Sep 14, 2026	72,604,668,609	1
Sep 13, 2026	55,872,948,637	1
Sep 12, 2026	48,637,635,954	1
Sep 11, 2026	61,154,457,835	1
Sep 10, 2026	61,445,647,589	1
Sep 9, 2026	53,377,229,975	1
Sep 8, 2026	55,412,654,953	1
Sep 7, 2026	45,809,813,103	1
Sep 6, 2026	41,196,636,949	1
Sep 5, 2026	40,127,893,080	1
Sep 4, 2026	70,704,483,461	1
Sep 3, 2026	74,829,968,678	1
Sep 2, 2026	67,837,314,055	1

Source: OpenRouter (openrouter.ai/rankings), as of Oct 24, 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-5.1Observed Oct 10, 2026, 11:31 AM UTC

Context: 1,000,000
Maximum output: 128,000
Tokenizer: Claude
Input: text, image, file
Output: text
Moderation: Yes
Added to OpenRouter: 2026-09-01

Base URLhttps://openrouter.ai/api/v1

Model IDanthropic/claude-fable-5.1

Version IDanthropic/claude-fable-5.1-20260831

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 5.1 cost?

Listed rates start at $10.00 per million input tokens and $50.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Claude Fable 5.1?

There are 46 cataloged offers across 37 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: Not reported. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 3 recorded revisions

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

Oct 19, 2026 · 2754589b6abb
Sep 14, 2026 · 4c2ede36ea1e
Sep 12, 2026 · 180bf8b72ddc