anthropic/claude-fable-5.1

模型发布 OpenRouter 模型 原文语言:中文

OpenRouter 于 2026-09-02 收录该模型(收录时间不等于模型正式发布日期);上下文:1,000,000 tokens;输入价:$10.0000/百万 tokens;输出价:$50.0000/百万 tokens;定位(来源描述):Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic…

全文

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 moreOpens in new tab

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

Compare

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

$10.00$50.00$0.2503.25s70 tok/s

99.91%

$10.00$50.00$0.2503.90s63 tok/s

99.77%

$10.00$50.00$0.2504.49s62 tok/s

99.93%

BYOK only

$10.00$50.00$0.2502.47s57 tok/s

--

Not used in Standard routing:Why these endpoints are not used

$11.00$55.00$0.275----

100.00%

ProviderInput / Output /M

Input $10.00 / Output $50.00

70 tok/s99.91% uptime

Input $10.00 / Output $50.00

63 tok/s99.77% uptime

Input $10.00 / Output $50.00

62 tok/s99.93% uptime

Input $10.00 / Output $50.00

BYOK only

57 tok/s-- uptime

Not used in Standard routing:Why these endpoints are not used

Input $11.00 / Output $55.00

-- tok/s100.00% 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

$1.687/M tokens

Output

$50/M tokens

Claude Fable 5.1 — Price history

Price history

No effective price data for this selection

$1.40$50.0090.8%55.8%

$1.96$50.0085.2%36.1%

$2.45$50.0081.3%8.0%

$3.75$50.0070.6%0.1%

Not used in Standard routing:Why these endpoints are not used

$11.00$55.000.0%0.0%

ProviderInput / Output /M

Token share

Effective in $1.40 / Effective out $50.00

Token share

55.8%

Effective in $1.96 / Effective out $50.00

Token share

36.1%

Effective in $2.45 / Effective out $50.00

Token share

8.0%

Effective in $3.75 / Effective out $50.00

Token share

0.1%

Not used in Standard routing:Why these endpoints are not used

Effective in $11.00 / Effective out $55.00

Token share

0.0%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

70tok/s

P50, best across providers

Latency

2.47s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchGoogle Vertex90.7%75.3%

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)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.83%

Availability over the last 3 days

Last 72 hours

Availability 99.83%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.98%

Without Routing

97.29%

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)

SourceBenchmarkScore

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) Intelligence Index49.2

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) Coding Index81.6

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) Agentic Index57.9

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) GPQA Diamond93.7%

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) HLE59.1%

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) AA-LCR85.3%

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) τ-Bench Banking47.2%

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) GDPval-AA63.2%

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) CritPt29.7%

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) SciCode63.1%

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) Terminal-Bench 4.052.0%

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) Terminal-Bench 2.191.4%

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) AA-Omniscience Accuracy68.4%

Artificial AnalysisClaude Fable 5.1 (Max, Default Fallback) AA-Omniscience Non-Hallucination Rate30.0%

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) Intelligence Index50.0

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) Coding Index80.7

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) Agentic Index57.2

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) GPQA Diamond93.4%

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) HLE58.7%

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) AA-LCR83.0%

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) τ-Bench Banking45.8%

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) GDPval-AA62.0%

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) CritPt31.1%

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) SciCode60.9%

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) Terminal-Bench 4.055.1%

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) Terminal-Bench 2.191.0%

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) AA-Omniscience Accuracy67.2%

Artificial AnalysisClaude Fable 5.1 (Xhigh, Default Fallback) AA-Omniscience Non-Hallucination Rate30.5%

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) Intelligence Index38.7

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) Coding Index75.2

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) Agentic Index47.1

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) GPQA Diamond88.1%

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) HLE48.9%

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) AA-LCR82.3%

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) τ-Bench Banking39.0%

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) GDPval-AA48.8%

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) CritPt27.7%

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) SciCode56.7%

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) Terminal-Bench 4.040.4%

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) Terminal-Bench 2.185.0%

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) AA-Omniscience Accuracy58.7%

Artificial AnalysisClaude Fable 5.1 (Low, Default Fallback) AA-Omniscience Non-Hallucination Rate40.2%

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) Intelligence Index47.2

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) Coding Index79.1

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) Agentic Index53.1

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) GPQA Diamond90.6%

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) HLE55.9%

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) AA-LCR83.7%

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) τ-Bench Banking43.1%

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) GDPval-AA57.2%

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) CritPt30.3%

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) SciCode58.7%

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) Terminal-Bench 4.052.0%

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) Terminal-Bench 2.189.9%

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) AA-Omniscience Accuracy64.7%

Artificial AnalysisClaude Fable 5.1 (High, Default Fallback) AA-Omniscience Non-Hallucination Rate29.8%

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) Intelligence Index43.2

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) Coding Index77.1

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) Agentic Index50.2

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) GPQA Diamond88.6%

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) HLE53.8%

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) AA-LCR84.7%

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) τ-Bench Banking41.0%

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) GDPval-AA52.7%

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) CritPt29.1%

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) SciCode56.4%

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) Terminal-Bench 4.044.9%

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) Terminal-Bench 2.188.0%

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) AA-Omniscience Accuracy62.6%

Artificial AnalysisClaude Fable 5.1 (Medium, Default Fallback) AA-Omniscience Non-Hallucination Rate30.2%

Design ArenaClaude Fable 5.1 Agents Arena Full Stack Elo1299

Design ArenaClaude Fable 5.1 Agents Arena Godotgamedev Elo1302

Design ArenaClaude Fable 5.1 Agents Arena Htmlslides Elo1390

Design ArenaClaude Fable 5.1 Agents Arena Mobile Apps Elo1253

Design ArenaClaude Fable 5.1 Agents Arena Python-Pptxslides Elo1316

Design ArenaClaude Fable 5.1 Agents Arena Spreadsheet Elo1346

Design ArenaClaude Fable 5.1 Agents Arena Webapps Elo1316

Design ArenaClaude Fable 5.1 Models Arena 3D Elo1388

Design ArenaClaude Fable 5.1 Models Arena Asciiart Elo1311

Design ArenaClaude Fable 5.1 Models Arena Code Categories Elo1330

Design ArenaClaude Fable 5.1 Models Arena Data Visualization Elo1344

Design ArenaClaude Fable 5.1 Models Arena Game Development Elo1364

Design ArenaClaude Fable 5.1 Models Arena SVG Elo1292

Design ArenaClaude Fable 5.1 Models Arena UI Component Elo1332

Design ArenaClaude Fable 5.1 Models Arena Website Elo1305

Vals AIClaude Fable 5.1 Code Migration54.6%

Vals AIClaude Fable 5.1 CyberBench v1.170.4%

Vals AIClaude Fable 5.1 EMB v1.176.7%

Vals AIClaude Fable 5.1 Finance Agent (v2)58.9%

Vals AIClaude Fable 5.1 Financial Coaching Bench75.7%

Vals AIClaude Fable 5.1 GPQA Diamond93.4%

Vals AIClaude Fable 5.1 Harvey's Legal Agent Benchmark v16.7%

Vals AIClaude Fable 5.1 Immigration75.4%

Vals AIClaude Fable 5.1 IOI90.8%

Vals AIClaude Fable 5.1 LiveCodeBench90.5%

Vals AIClaude Fable 5.1 LegalBench88.5%

Vals AIClaude Fable 5.1 Legal Research Bench55.3%

Vals AIClaude Fable 5.1 MedCode53.5%

Vals AIClaude Fable 5.1 MedScribe91.3%

Vals AIClaude Fable 5.1 MMLU Pro92.4%

Vals AIClaude Fable 5.1 MMMU Pro90.6%

Vals AIClaude Fable 5.1 MortgageTax70.8%

Vals AIClaude Fable 5.1 MysteryMechanism47.7%

Vals AIClaude Fable 5.1 ProgramBench7.0%

Vals AIClaude Fable 5.1 ProofBench v1.1100.0%

Vals AIClaude Fable 5.1 Public Benefits Bench v1.174.9%

Vals AIClaude Fable 5.1 Robo-bench5.8%

Vals AIClaude Fable 5.1 Vals RSI Index36.1%

Vals AIClaude Fable 5.1 SAGE v148.5%

Vals AIClaude Fable 5.1 SkillsBench61.6%

Vals AIClaude Fable 5.1 SRE Bench22.9%

Vals AIClaude Fable 5.1 SWE-bench Multimodal61.3%

Vals AIClaude Fable 5.1 Tax Agent Bench50.7%

Vals AIClaude Fable 5.1 TaxEval v276.0%

Vals AIClaude Fable 5.1 Terminal-Bench 4.058.1%

Vals AIClaude Fable 5.1 Terminal-Bench-Science40.0%

Vals AIClaude Fable 5.1 Vals Index65.8%

Vals AIClaude Fable 5.1 Vibe Code Bench 1-10028.0%

Vals AIClaude Fable 5.1 Vibe Code Bench v1.190.3%

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.

1.

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.

218Btokens

2.

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.

149Btokens

3.

omp

new

18.6Btokens

4.

pi

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

18.1Btokens

5.

OpenHands

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

13.3Btokens

Rest of OpenRouter

2.84B

Top 5 Apps

2.4B

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Anthropic: Claude Fable versions

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

Documentation

Guides, cookbooks, blog posts, and tools for building with Anthropic: Claude Fable 5.1 on OpenRouter.

Claude Fable 5.1 Migration GuideCookbook

Frequently asked questions

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.

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.

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.

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

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.

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

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.

Claude Fable 5.1 was released on September 1, 2026.

正文以来源语言显示。

参考来源

← 返回每日简报