OpenRouter 模型 ↗ · 2026-11-10
anthropic/claude-fable-5.2
Model release OpenRouter 模型 Source language: Chinese
OpenRouter 于 2026-11-10 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:$8.0000/百万 tokens;输出价:$40.0000/百万 tokens;定位(来源描述):Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with…
Full text
By using Claude Fable 5.2, 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 5.2
anthropic/claude-fable-5.2
Compare
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.
Modalities
In / out price
$8 / $40per 1M
Context
1.0M
Released
Nov 9, 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
$8.00$40.00$0.203.56s85 tok/s
99.06%
$8.00$40.00$0.203.69s77 tok/s
99.89%
$8.00$40.00$0.205.01s72 tok/s
99.23%
BYOK only
$8.00$40.00$0.205.93s87 tok/s
--
Not used in Standard routing:Why these endpoints are not used
Fast
$16.00$80.00$0.402.66s167 tok/s
100.00%
ProviderInput / Output /M
Input $8.00 / Output $40.00
85 tok/s99.06% uptime
Input $8.00 / Output $40.00
77 tok/s99.89% uptime
Input $8.00 / Output $40.00
72 tok/s99.23% uptime
Input $8.00 / Output $40.00
BYOK only
87 tok/s-- uptime
Not used in Standard routing:Why these endpoints are not used
Input $16.00 / Output $80.00
Fast
167 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
$1.124/M tokens
Output
$41.16/M tokens
Claude Fable 5.2 — Price history
Price history
No effective price data for this selection
$0.884$40.0092.9%1.2%
$0.968$40.0092.0%12.5%
$1.093$40.0089.9%68.5%
$1.397$40.0087.0%14.5%
Not used in Standard routing:Why these endpoints are not used
Fast
$1.267$80.0095.6%3.3%
ProviderInput / Output /M
Token share
Effective in $0.884 / Effective out $40.00
Token share
1.2%
Effective in $0.968 / Effective out $40.00
Token share
12.5%
Effective in $1.093 / Effective out $40.00
Token share
68.5%
Effective in $1.397 / Effective out $40.00
Token share
14.5%
Not used in Standard routing:Why these endpoints are not used
Effective in $1.267 / Effective out $80.00
FastToken share
3.3%
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
167tok/s
P50, best across providers
Latency
2.66s
P50, best provider
Reasoning effortLatency / throughput
AutoExacto benchmarks
GPQA DiamondTAU-BenchAnthropic95.1%71.3%Azure94.9%68.0%Google Vertex94.6%68.0%
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)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.
99.53%
Availability over the last 3 days
Last 72 hours
Availability 99.53%
3 Days Ago2 Days AgoYesterdayNow
Availability over the last 24 hours
OpenRouter Availability
99.94%
Without Routing
96.60%
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 5.2 (Artificial Analysis, Design Arena and Vals AI)
SourceBenchmarkScore
Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) Intelligence Index64.6
Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) HLE74.3%
Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) AA-LCR83.3%
Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) GDPval-AA66.6%
Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) CritPt35.4%
Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) SciCode67.7%
Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) AA-Omniscience Accuracy79.1%
Artificial AnalysisClaude Fable 5.2 (Max, Default Fallback) AA-Omniscience Non-Hallucination Rate40.7%
Design ArenaClaude Fable 5.2 Agents Arena Codetovideo Elo1429
Design ArenaClaude Fable 5.2 Agents Arena Full Stack Elo1400
Design ArenaClaude Fable 5.2 Agents Arena Mobile Apps Elo1322
Design ArenaClaude Fable 5.2 Agents Arena Pdf Elo1322
Design ArenaClaude Fable 5.2 Agents Arena Spreadsheet Elo1434
Design ArenaClaude Fable 5.2 Models Arena 3D Elo1501
Design ArenaClaude Fable 5.2 Models Arena Code Categories Elo1375
Design ArenaClaude Fable 5.2 Models Arena Game Development Elo1399
Design ArenaClaude Fable 5.2 Models Arena UI Component Elo1382
Design ArenaClaude Fable 5.2 Models Arena Website Elo1352
Vals AIClaude Fable 5.2 BioMysteryBench83.7%
Vals AIClaude Fable 5.2 Code Migration v1.183.3%
Vals AIClaude Fable 5.2 EMB v1.177.4%
Vals AIClaude Fable 5.2 Finance Agent v2.169.5%
Vals AIClaude Fable 5.2 Vals Finance Index63.6%
Vals AIClaude Fable 5.2 HLAB-Vals-1.15.0%
Vals AIClaude Fable 5.2 Immigration74.0%
Vals AIClaude Fable 5.2 Vals Legal Index69.2%
Vals AIClaude Fable 5.2 Legal Research Bench46.2%
Vals AIClaude Fable 5.2 MysteryMechanism51.8%
Vals AIClaude Fable 5.2 ProgramBench19.0%
Vals AIClaude Fable 5.2 ProofBench v1.1100.0%
Vals AIClaude Fable 5.2 Vals RSI Index37.9%
Vals AIClaude Fable 5.2 Vals Science Index63.7%
Vals AIClaude Fable 5.2 SWE-bench Multimodal62.3%
Vals AIClaude Fable 5.2 Tax Agent Bench32.1%
Vals AIClaude Fable 5.2 Terminal-Bench 4.065.2%
Vals AIClaude Fable 5.2 Terminal-Bench-Science55.7%
Vals AIClaude Fable 5.2 Vals Index71.3%
Vals AIClaude Fable 5.2 Vibe Code Bench v1.193.8%
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.
312Btokens
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.
62.7Btokens
3.
pi
There are many coding agents, but this one is yours.
20.4Btokens
4.
omp
new
11.1Btokens
5.
bcode
new
7.18Btokens
Rest of OpenRouter
46.2B
Top 5 Apps
24.4B
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
Frequently asked questions
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.
Claude Fable 5.2 costs $8.00/M input tokens and $40.00/M output tokens, with separate rates for Cache Read at $0.20/M tokens, Cache Write at $10.00/M tokens, and Cache Write (1h) at $16.00/M tokens.
Claude Fable 5.2 has a 1,000,000 token context window. It supports up to 128,000 completion tokens.
Yes. Claude Fable 5.2 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Claude Fable 5.2 accepts text, images, and files such as PDFs as input and returns text.
Claude Fable 5.2 is served by 4 providers on OpenRouter: Google Vertex, Amazon Bedrock, Azure, and Anthropic. 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 5.2 was released on November 9, 2026.