Where is the Claude Fable 5.1 documentation?

The Claude Fable 5.1 documentation on OpenRouter includes the Claude Fable 5.1 Migration Guide cookbook. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does Claude Fable 5.1 cost?

Claude Fable 5.1 costs $10.00/M input tokens and $50.00/M output tokens, with separate rates for Cache Read at $0.25/M tokens, Cache Write at $12.50/M tokens, and Cache Write (1h) at $20.00/M tokens.

What is the context length of Claude Fable 5.1?

Claude Fable 5.1 has a 1,000,000 token context window. It supports up to 128,000 completion tokens.

Does Claude Fable 5.1 support tool calling and structured outputs?

Yes. Claude Fable 5.1 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does Claude Fable 5.1 support?

Claude Fable 5.1 accepts text, images, and files such as PDFs as input and returns text.

Which providers serve Claude Fable 5.1?

Claude Fable 5.1 is served by 4 providers on OpenRouter: Azure, Anthropic, Amazon Bedrock, and Google Vertex. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Claude Fable 5.1 released?

Claude Fable 5.1 was released on September 1, 2026.

By using Claude Fable 5.1, you consent to data retention for purposes of monitoring safe and compliant use of AI. Anthropic's data retention policy does not allow zero data retention. Learn more

Amazon Bedrock endpoint is BYOK-only while we work on enabling public access.

Anthropic: Claude Fable 5.1

anthropic/claude-fable-5.1

Compare

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.

Modalities

In / out price

$10 / $50per 1M

Context

1.0M

Released

Sep 1, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


BYOK only	$10.00	$50.00	$0.25	10.89s	51 tok/s	--
	$10.00	$50.00	$0.25	3.03s	69 tok/s	99.94%
	$10.00	$50.00	$0.25	3.58s	60 tok/s	98.81%
	$10.00	$50.00	$0.25	4.73s	59 tok/s	99.54%
Not used in Standard routing:Why these endpoints are not used
	$11.00	$55.00	$0.275	--	--	--

Input $10.00Output $50.00
BYOK only
51 tok/s-- uptime
Input $10.00Output $50.00
69 tok/s99.94% uptime
Input $10.00Output $50.00
60 tok/s98.81% uptime
Input $10.00Output $50.00
59 tok/s99.54% uptime
Not used in Standard routing:Why these endpoints are not used
Input $11.00Output $55.00
-- tok/s-- uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$1.349/M tokens

Output

$50/M tokens

Claude Fable 5.1 — Price history

Price history

No effective price data for this selection

	$1.29	$50.00	91.8%	49.1%
	$1.31	$50.00	91.9%	13.7%
	$1.43	$50.00	90.6%	37.1%
	$3.90	$50.00	72.7%	0.1%
Not used in Standard routing:Why these endpoints are not used
	$11.00	$55.00	0.0%	0.0%

Effective in $1.29Effective out $50.00
Token share
49.1%
Effective in $1.31Effective out $50.00
Token share
13.7%
Effective in $1.43Effective out $50.00
Token share
37.1%
Effective in $3.90Effective out $50.00
Token share
0.1%
Not used in Standard routing:Why these endpoints are not used
Effective in $11.00Effective out $55.00
Token share
0.0%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.85%

Availability over the last 3 days

Last 72 hours

Availability 99.85%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.62%

Without Routing

97.09%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Anthropic: Claude Fable 5.1 (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) Intelligence Index	49.2
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) Coding Index	81.6
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) Agentic Index	57.9
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) GPQA Diamond	93.7%
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) HLE	59.1%
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) AA-LCR	85.3%
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) τ-Bench Banking	47.2%
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) GDPval-AA	63.2%
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) CritPt	29.7%
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) SciCode	63.1%
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) Terminal-Bench 4.0	52.0%
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) Terminal-Bench 2.1	91.4%
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) AA-Omniscience Accuracy	68.4%
Artificial Analysis	Claude Fable 5.1 (Max, Default Fallback) AA-Omniscience Non-Hallucination Rate	30.0%
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) Intelligence Index	50.0
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) Coding Index	80.7
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) Agentic Index	57.2
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) GPQA Diamond	93.4%
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) HLE	58.7%
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) AA-LCR	83.0%
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) τ-Bench Banking	45.8%
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) GDPval-AA	62.0%
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) CritPt	31.1%
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) SciCode	60.9%
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) Terminal-Bench 4.0	55.1%
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) Terminal-Bench 2.1	91.0%
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) AA-Omniscience Accuracy	67.2%
Artificial Analysis	Claude Fable 5.1 (Xhigh, Default Fallback) AA-Omniscience Non-Hallucination Rate	30.5%
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) Intelligence Index	38.7
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) Coding Index	75.2
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) Agentic Index	47.1
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) GPQA Diamond	88.1%
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) HLE	48.9%
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) AA-LCR	82.3%
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) τ-Bench Banking	39.0%
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) GDPval-AA	48.8%
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) CritPt	27.7%
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) SciCode	56.7%
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) Terminal-Bench 4.0	40.4%
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) Terminal-Bench 2.1	85.0%
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) AA-Omniscience Accuracy	58.7%
Artificial Analysis	Claude Fable 5.1 (Low, Default Fallback) AA-Omniscience Non-Hallucination Rate	40.2%
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) Intelligence Index	47.2
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) Coding Index	79.1
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) Agentic Index	53.1
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) GPQA Diamond	90.6%
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) HLE	55.9%
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) AA-LCR	83.7%
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) τ-Bench Banking	43.1%
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) GDPval-AA	57.2%
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) CritPt	30.3%
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) SciCode	58.7%
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) Terminal-Bench 4.0	52.0%
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) Terminal-Bench 2.1	89.9%
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) AA-Omniscience Accuracy	64.7%
Artificial Analysis	Claude Fable 5.1 (High, Default Fallback) AA-Omniscience Non-Hallucination Rate	29.8%
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) Intelligence Index	43.2
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) Coding Index	77.1
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) Agentic Index	50.2
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) GPQA Diamond	88.6%
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) HLE	53.8%
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) AA-LCR	84.7%
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) τ-Bench Banking	41.0%
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) GDPval-AA	52.7%
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) CritPt	29.1%
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) SciCode	56.4%
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) Terminal-Bench 4.0	44.9%
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) Terminal-Bench 2.1	88.0%
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) AA-Omniscience Accuracy	62.6%
Artificial Analysis	Claude Fable 5.1 (Medium, Default Fallback) AA-Omniscience Non-Hallucination Rate	30.2%
Design Arena	Claude Fable 5.1 Agents Arena Full Stack Elo	1301
Design Arena	Claude Fable 5.1 Agents Arena Godotgamedev Elo	1304
Design Arena	Claude Fable 5.1 Agents Arena Htmlslides Elo	1390
Design Arena	Claude Fable 5.1 Agents Arena Mobile Apps Elo	1253
Design Arena	Claude Fable 5.1 Agents Arena Python-Pptxslides Elo	1316
Design Arena	Claude Fable 5.1 Agents Arena Spreadsheet Elo	1346
Design Arena	Claude Fable 5.1 Agents Arena Webapps Elo	1313
Design Arena	Claude Fable 5.1 Models Arena 3D Elo	1387
Design Arena	Claude Fable 5.1 Models Arena Asciiart Elo	1318
Design Arena	Claude Fable 5.1 Models Arena Code Categories Elo	1330
Design Arena	Claude Fable 5.1 Models Arena Data Visualization Elo	1345
Design Arena	Claude Fable 5.1 Models Arena Game Development Elo	1364
Design Arena	Claude Fable 5.1 Models Arena SVG Elo	1293
Design Arena	Claude Fable 5.1 Models Arena UI Component Elo	1332
Design Arena	Claude Fable 5.1 Models Arena Website Elo	1305
Vals AI	Claude Fable 5.1 Code Migration	54.6%
Vals AI	Claude Fable 5.1 CyberBench v1.1	70.4%
Vals AI	Claude Fable 5.1 EMB v1.1	76.7%
Vals AI	Claude Fable 5.1 Finance Agent (v2)	58.9%
Vals AI	Claude Fable 5.1 Financial Coaching Bench	75.7%
Vals AI	Claude Fable 5.1 GPQA Diamond	93.4%
Vals AI	Claude Fable 5.1 Harvey's Legal Agent Benchmark v1	6.7%
Vals AI	Claude Fable 5.1 Immigration	75.4%
Vals AI	Claude Fable 5.1 IOI	90.8%
Vals AI	Claude Fable 5.1 LiveCodeBench	90.5%
Vals AI	Claude Fable 5.1 LegalBench	88.5%
Vals AI	Claude Fable 5.1 Legal Research Bench	55.3%
Vals AI	Claude Fable 5.1 MedCode	53.5%
Vals AI	Claude Fable 5.1 MedScribe	91.3%
Vals AI	Claude Fable 5.1 MMLU Pro	92.4%
Vals AI	Claude Fable 5.1 MMMU Pro	90.6%
Vals AI	Claude Fable 5.1 MortgageTax	70.8%
Vals AI	Claude Fable 5.1 MysteryMechanism	47.7%
Vals AI	Claude Fable 5.1 ProgramBench	7.0%
Vals AI	Claude Fable 5.1 ProofBench v1.1	100.0%
Vals AI	Claude Fable 5.1 Public Benefits Bench v1.1	74.9%
Vals AI	Claude Fable 5.1 Robo-bench	5.8%
Vals AI	Claude Fable 5.1 Vals RSI Index	36.1%
Vals AI	Claude Fable 5.1 SAGE v1	48.5%
Vals AI	Claude Fable 5.1 SkillsBench	61.6%
Vals AI	Claude Fable 5.1 SRE Bench	22.9%
Vals AI	Claude Fable 5.1 SWE-bench Multimodal	61.3%
Vals AI	Claude Fable 5.1 Tax Agent Bench	50.7%
Vals AI	Claude Fable 5.1 TaxEval v2	76.0%
Vals AI	Claude Fable 5.1 Terminal-Bench 4.0	58.1%
Vals AI	Claude Fable 5.1 Terminal-Bench-Science	40.0%
Vals AI	Claude Fable 5.1 Vals Index	65.8%
Vals AI	Claude Fable 5.1 Vibe Code Bench 1-100	28.0%
Vals AI	Claude Fable 5.1 Vibe Code Bench v1.1	90.3%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

225Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

161Btokens

omp

new

20.9Btokens

There are many coding agents, but this one is yours.

19Btokens

OpenHands

AI coding agent that can run commands, browse the web, call APIs

13.3Btokens

Rest of OpenRouter

2.56B

Top 5 Apps

1.65B

Anthropic: Claude Fable versions

Not currently available through EU in-region routing. In-region routing docs

More models from Anthropic

Claude Fable 5.2

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible software migrations, designed working electronic devices from scratch, and made progress on open problems in physics and mathematics. It communicates more clearly than earlier Fable models and generates output up to 30% faster than Fable 5.1. Adaptive extended thinking is always on, with reasoning effort levels from low to max (default high) and preserved thinking across turns. Anthropic recommends Opus 5.5 as the daily driver for most coding and knowledge work, with Fable 5.2 for the most ambitious, open-ended problems.

Text1M context$8 / $40

Claude Fable 5.2 (batch)

Text1M context$4 / $20

Claude Haiku 5.5

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window.

It is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.

Text1M context$0.10 / $0.50

Claude Haiku 5.5 (batch)

Text1M context$0.05 / $0.25

Claude Sonnet 5.5

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor.

Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.

Text1M context$2 / $10

Claude Sonnet 5.5 (batch)

Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.

Text1M context$1 / $5

Claude Opus 5.5

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.

The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.

Text1M context$4 / $20

Claude Opus 5.5 (batch)

Text1M context$2 / $10

Claude Fable 5.1

Text1M context$10 / $50

Claude Fable 5.1 (batch)

Text1M context$5 / $25

Claude Opus 5

Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 5 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

Text1M context

Claude Opus 5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

Text1M context$5 / $25

Claude Opus 5 (batch)

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

Text1M context$2.50 / $12.50

Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.

Text1M context$2 / $10

Claude Sonnet 5 (batch)

Text1M context$1 / $5

Claude Fable Latest

This model always redirects to the latest model in the Claude Fable family.

Text1M context

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.

Text1M context$10 / $50

Claude Fable 5 (batch)

Text1M context$5 / $25

Claude Opus 4.8

Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 4.8 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

Text1M context

Claude Opus 4.8

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.

It is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.

Text1M context$5 / $25

Anthropic: Claude Fable 5.1

Providers