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
Family: claude-fable
Providers: 45
Context: 1,000,000
Output limit: 128,000
Knowledge: 2026-01-31
Release: 2026-06-09
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.

56 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
302.AI	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Abacus	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
AIHubMix	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
AI/ML API	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Amazon Bedrock	anthropic.claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Amazon Bedrock	global.anthropic.claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Amazon Bedrock	eu.anthropic.claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Amazon Bedrock	us.anthropic.claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Azure	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Cloudflare AI Gateway	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
CommandCode	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
CrossModel	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Deep Infra	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
DevPass (LLM Gateway)	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
DigitalOcean	anthropic-claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Eden AI	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
FreeModel	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
GitHub Copilot	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
GitLab Duo	duo-chat-fable-5	1,000,000	128,000	— / —	—	—	—	View
Impossibl	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Kenari	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Kilo Gateway	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
LLM Gateway	aws-bedrock/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
LLM Gateway	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
LLM Gateway	azure-anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Merge Gateway	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Modelis	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Model Oracle AI	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
NanoGPT	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
NEAR AI Cloud	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Neon	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Ofox	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
OpenCode	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Amazon Bedrockvia OpenRouter	anthropic/claude-fable-5 unknown	1,000,000	128,000	$10.00 / $50.00	Yes	Yes	No	View
Anthropicvia OpenRouter	anthropic/claude-fable-5 unknown	1,000,000	128,000	$10.00 / $50.00	Yes	Yes	Yes	View
Azurevia OpenRouter	anthropic/claude-fable-5 unknown	1,000,000	128,000	$10.00 / $50.00	Yes	Yes	Yes	View
Claude Platform on AWSvia OpenRouter	anthropic/claude-fable-5 unknown	1,000,000	128,000	$10.00 / $50.00	Yes	Yes	Yes	View
Googlevia OpenRouter	anthropic/claude-fable-5 unknown	1,000,000	128,000	$11.00 / $55.00	Yes	Yes	Yes	View
Googlevia OpenRouter	anthropic/claude-fable-5 unknown	1,000,000	128,000	$10.00 / $50.00	Yes	Yes	Yes	View
Opper	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
OrcaRouter	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Perplexity Agent	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Pioneer	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Prime Inference	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Requesty	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Requesty	claude-fable-5@eu	1,000,000	128,000	— / —	—	—	—	View
Snowflake Cortex	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Standard Compute	anthropic/claude-fable-5	1,000,000	50,000	— / —	—	—	—	View
Tempr Gateway	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Venice AI	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Vercel AI Gateway	anthropic/claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Vertex	claude-fable-5@default	1,000,000	128,000	— / —	—	—	—	View
Vertex (Anthropic)	claude-fable-5@default	1,000,000	128,000	— / —	—	—	—	View
Vivgrid	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
Xpersona	claude-fable-5	1,000,000	128,000	— / —	—	—	—	View
ZenMux	anthropic/claude-fable-5	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 offers56Across 45 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 Oct 10, 2026, 11:31 AM UTC

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

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache 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 · 6 endpoints

P50P75P90P99

Amazon Bedrockamazon-bedrock

3,688–5,708.74 ms

Anthropicanthropic

2,989.5–10,131.79 ms

Azureazure

5,245.5–5,870.52 ms

Claude Platform on AWSclaude-on-aws

3,462.5–6,060.91 ms

Googlegoogle-vertex/europe

928–11,655.08 ms

Googlegoogle-vertex/global

4,354–5,255.6 ms

All latency percentiles 6 endpoints

Endpoint	P50	P75	P90	P99
Amazon Bedrockamazon-bedrock	3,688 ms	5,016.5 ms	5,211 ms	5,708.74 ms
Anthropicanthropic	2,989.5 ms	4,332.75 ms	5,383.2 ms	10,131.79 ms
Azureazure	5,245.5 ms	5,859 ms	5,866.2 ms	5,870.52 ms
Claude Platform on AWSclaude-on-aws	3,462.5 ms	4,378 ms	5,090.8 ms	6,060.91 ms
Googlegoogle-vertex/europe	928 ms	6,401 ms	9,684.8 ms	11,655.08 ms
Googlegoogle-vertex/global	4,354 ms	4,814 ms	5,090 ms	5,255.6 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Amazon Bedrockamazon-bedrock

33–89.11 t/s

Anthropicanthropic

55–106 t/s

Azureazure

41–44.94 t/s

Claude Platform on AWSclaude-on-aws

43–86.73 t/s

Googlegoogle-vertex/europe

64–94.38 t/s

Googlegoogle-vertex/global

53.5–53.99 t/s

All throughput percentiles 6 endpoints

Endpoint	P50	P75	P90	P99
Amazon Bedrockamazon-bedrock	33 t/s	47.75 t/s	53.9 t/s	89.11 t/s
Anthropicanthropic	55 t/s	70 t/s	82 t/s	106 t/s
Azureazure	41 t/s	43.5 t/s	44.4 t/s	44.94 t/s
Claude Platform on AWSclaude-on-aws	43 t/s	56 t/s	68 t/s	86.73 t/s
Googlegoogle-vertex/europe	64 t/s	79.5 t/s	88.8 t/s	94.38 t/s
Googlegoogle-vertex/global	53.5 t/s	53.75 t/s	53.9 t/s	53.99 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-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%

Claude Platform on AWSclaude-on-awsObserved Oct 10, 2026, 11:31 AM UTC

100%

Googlegoogle-vertex/europeObserved 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-5Observed Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 80

Coding

76.5

Agentic

50.7

Intelligence

49.6

Design Arena	Category	Elo	Win rate	Rank
agents	agenticgamedev	1,285	61.9%	1
agents	agentichtmlslides	1,254	59.4%	1
agents	agenticslides(html)	1,252	59.5%	1
agents	androidnative	1,297	65.1%	2
agents	fullstack	1,280	58.2%	6
agents	godotgamedev	1,292	64.3%	2
agents	htmlslides	1,277	63.1%	1
agents	mobileapps	1,259	60.5%	5
agents	python-pptxslides	1,295	61.4%	3
agents	webapps	1,254	56.4%	8
models	3d	1,324	61.8%	10
models	asciiart	1,333	68%	2
models	codecategories	1,315	57.7%	8
models	dataviz	1,309	57.6%	12
models	gamedev	1,343	60.8%	8
models	svg	1,303	62.6%	5
models	uicomponent	1,322	58.1%	10
models	website	1,300	56%	14

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

tau bench verified airlineAnthropic: Claude Fable 5

80.182%

gpqa diamondAnthropic: Claude Fable 5

86.139%

Evaluation	Configuration	Source	Results	Details
models · asciiart	Claude Fable 5anthropic/claude-5-fable-20260609	Design Arena	1,329 Elo	Details
tau bench verified airline	Anthropic: Claude Fable 5anthropic/claude-5-fable-20260609	OpenRouter	80.182%	Details
models · svg	Claude Fable 5anthropic/claude-5-fable-20260609	Design Arena	1,303 Elo	Details
models · uicomponent	Claude Fable 5anthropic/claude-5-fable-20260609	Design Arena	1,316 Elo	Details
models · codecategories	Claude Fable 5anthropic/claude-5-fable-20260609	Design Arena	1,310 Elo	Details
models · gamedev	Claude Fable 5anthropic/claude-5-fable-20260609	Design Arena	1,335 Elo	Details
Composite indices	Claude Fable 5 (Max, Opus 4.8 Fallback)anthropic/claude-5-fable-20260609	Artificial Analysis	Intelligence 49.6 · Coding 76.5 · Agentic 50.7	Details
gpqa diamond	Anthropic: Claude Fable 5anthropic/claude-5-fable-20260609	OpenRouter	86.139%	Details
models · website	Claude Fable 5anthropic/claude-5-fable-20260609	Design Arena	1,296 Elo	Details
models · dataviz	Claude Fable 5anthropic/claude-5-fable-20260609	Design Arena	1,304 Elo	Details
models · 3d	Claude Fable 5anthropic/claude-5-fable-20260609	Design Arena	1,319 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
Claude Code	anthropic/claude-5-fable-20260609	1 turn	$0.026727	Details
Claude Code	anthropic/claude-5-fable-20260609	2–9 turns	$0.778244	Details
Hermes Agent	anthropic/claude-5-fable-20260609	10–49 turns	$3.724561	Details
Claude Code	anthropic/claude-5-fable-20260609	10–49 turns	$4.502273	Details
Hermes Agent	anthropic/claude-5-fable-20260609	2–9 turns	$0.718079	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 usage1,284,702,886,964 reported tokens · 36 days with observations

49B0

2026-07-27
33,561,574,342 tokens

2026-07-28
35,467,023,275 tokens

2026-07-29
37,210,310,013 tokens

2026-07-30
31,620,928,592 tokens

2026-07-31
35,280,739,315 tokens

2026-08-01
21,846,491,561 tokens

2026-08-02
23,607,616,203 tokens

2026-08-03
35,265,680,406 tokens

2026-08-04
38,851,050,476 tokens

2026-08-05
39,691,950,478 tokens

2026-08-06
30,738,585,057 tokens

2026-08-07
30,513,079,917 tokens

2026-08-08
30,467,132,649 tokens

2026-08-09
21,309,456,046 tokens

2026-08-10
34,621,678,351 tokens

2026-08-11
41,321,247,641 tokens

2026-08-12
49,352,997,385 tokens

2026-08-13
47,151,354,478 tokens

2026-08-14
34,536,732,806 tokens

2026-08-15
32,553,972,618 tokens

2026-08-16
30,345,083,508 tokens

2026-08-17
47,550,444,993 tokens

2026-08-18
43,052,485,662 tokens

2026-08-19
44,738,863,867 tokens

2026-08-20
47,031,536,787 tokens

2026-08-21
38,767,734,248 tokens

2026-08-22
26,615,977,244 tokens

2026-08-23
22,522,875,114 tokens

2026-08-24
33,415,623,224 tokens

2026-08-25
40,123,386,315 tokens

2026-08-26
37,977,154,913 tokens

2026-08-27
38,942,806,078 tokens

2026-08-28
33,553,366,144 tokens

2026-08-31
37,104,844,949 tokens

2026-09-01
37,242,219,097 tokens

2026-09-14
40,748,883,212 tokens

Jul 26, 2026Oct 23, 2026

Daily observations · 36 days

Date (UTC)	Reported tokens	Reported routes
Sep 14, 2026	40,748,883,212	1
Sep 1, 2026	37,242,219,097	1
Aug 31, 2026	37,104,844,949	1
Aug 28, 2026	33,553,366,144	1
Aug 27, 2026	38,942,806,078	1
Aug 26, 2026	37,977,154,913	1
Aug 25, 2026	40,123,386,315	1
Aug 24, 2026	33,415,623,224	1
Aug 23, 2026	22,522,875,114	1
Aug 22, 2026	26,615,977,244	1
Aug 21, 2026	38,767,734,248	1
Aug 20, 2026	47,031,536,787	1
Aug 19, 2026	44,738,863,867	1
Aug 18, 2026	43,052,485,662	1
Aug 17, 2026	47,550,444,993	1
Aug 16, 2026	30,345,083,508	1
Aug 15, 2026	32,553,972,618	1
Aug 14, 2026	34,536,732,806	1
Aug 13, 2026	47,151,354,478	1
Aug 12, 2026	49,352,997,385	1
Aug 11, 2026	41,321,247,641	1
Aug 10, 2026	34,621,678,351	1
Aug 9, 2026	21,309,456,046	1
Aug 8, 2026	30,467,132,649	1
Aug 7, 2026	30,513,079,917	1
Aug 6, 2026	30,738,585,057	1
Aug 5, 2026	39,691,950,478	1
Aug 4, 2026	38,851,050,476	1
Aug 3, 2026	35,265,680,406	1
Aug 2, 2026	23,607,616,203	1
Aug 1, 2026	21,846,491,561	1
Jul 31, 2026	35,280,739,315	1
Jul 30, 2026	31,620,928,592	1
Jul 29, 2026	37,210,310,013	1
Jul 28, 2026	35,467,023,275	1
Jul 27, 2026	33,561,574,342	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-5Observed 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: 2026-06-09

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 $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?

There are 56 cataloged offers across 45 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 · a11c8d6123cd
Sep 14, 2026 · b4368b89eb97
Sep 12, 2026 · 7949123b2808