OpenRouter 模型 ↗ · 2026-09-29
anthropic/claude-sonnet-5.5
模型发布 OpenRouter 模型 原文语言:中文
OpenRouter 于 2026-09-29 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:$2.0000/百万 tokens;输出价:$10.0000/百万 tokens;定位(来源描述):Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding…
全文
Anthropic: Claude Sonnet 5.5
anthropic/claude-sonnet-5.5
Compare
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.
Modalities
In / out price
$2 / $10per 1M
Context
1.0M
Released
Sep 28, 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
$2.00$10.00$0.101.15s105 tok/s
100.00%
$2.00$10.00$0.101.98s105 tok/s
100.00%
$2.00$10.00$0.100.81s104 tok/s
100.00%
$2.00$10.00$0.101.49s92 tok/s
100.00%
$2.00$10.00$0.102.98s102 tok/s
100.00%
Not used in Standard routing:Why these endpoints are not used
$2.20$11.00$0.110.89s110 tok/s
100.00%
$2.20$11.00$0.112.85s83 tok/s
100.00%
$2.20$11.00$0.111.98s104 tok/s
100.00%
$2.20$11.00$0.111.68s86 tok/s
100.00%
$2.20$11.00$0.111.82s91 tok/s
100.00%
ProviderInput / Output /M
Input $2.00 / Output $10.00
105 tok/s100.00% uptime
Input $2.00 / Output $10.00
105 tok/s100.00% uptime
Input $2.00 / Output $10.00
104 tok/s100.00% uptime
Input $2.00 / Output $10.00
92 tok/s100.00% uptime
Input $2.00 / Output $10.00
102 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $2.20 / Output $11.00
110 tok/s100.00% uptime
Input $2.20 / Output $11.00
83 tok/s100.00% uptime
Input $2.20 / Output $11.00
104 tok/s100.00% uptime
Input $2.20 / Output $11.00
86 tok/s100.00% uptime
Input $2.20 / Output $11.00
91 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
$0.6399/M tokens
Output
$10.03/M tokens
Claude Sonnet 5.5 — Price history
Price history
No effective price data for this selection
$0.383$10.0087.7%13.8%
$0.563$10.0078.9%22.2%
$0.708$10.0070.5%41.4%
$0.725$10.0079.5%15.7%
$0.880$10.0064.4%0.8%
Not used in Standard routing:Why these endpoints are not used
$0.348$11.0091.1%0.4%
$0.590$11.0079.4%1.0%
$0.622$11.0077.7%0.6%
$0.892$11.0080.4%4.2%
$2.200$11.000.0%0.0%
ProviderInput / Output /M
Token share
Effective in $0.383 / Effective out $10.00
Token share
13.8%
Effective in $0.563 / Effective out $10.00
Token share
22.2%
Effective in $0.708 / Effective out $10.00
Token share
41.4%
Effective in $0.725 / Effective out $10.00
Token share
15.7%
Effective in $0.880 / Effective out $10.00
Token share
0.8%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.348 / Effective out $11.00
Token share
0.4%
Effective in $0.590 / Effective out $11.00
Token share
1.0%
Effective in $0.622 / Effective out $11.00
Token share
0.6%
Effective in $0.892 / Effective out $11.00
Token share
4.2%
Effective in $2.200 / Effective out $11.00
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
110tok/s
P50, best across providers
Latency
0.81s
P50, best provider
Reasoning effortLatency / throughput
AutoExacto benchmarks
GPQA DiamondTAU-Benchauto-routing93.2%79.3%Google Vertex (US)93.0%78.9%Amazon Bedrock (EU)92.5%79.3%Anthropic92.7%78.6%Azure (US)92.0%78.6%Amazon Bedrock (US)92.3%78.3%Google Vertex93.2%76.9%Azure91.9%78.0%Amazon Bedrock92.8%75.9%Google Vertex (EU)92.5%76.0%
+1 more providers
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.
99.91%
Availability over the last 3 days
Last 72 hours
Availability 99.91%
3 Days Ago2 Days AgoYesterdayNow
Availability over the last 24 hours
OpenRouter Availability
99.96%
Without Routing
99.00%
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 Sonnet 5.5 (Artificial Analysis, Design Arena and Vals AI)
SourceBenchmarkScore
Artificial AnalysisClaude Sonnet 5.5 (Low, Default Fallback) Intelligence Index25.6
Artificial AnalysisClaude Sonnet 5.5 (Low, Default Fallback) HLE36.2%
Artificial AnalysisClaude Sonnet 5.5 (Low, Default Fallback) AA-LCR76.0%
Artificial AnalysisClaude Sonnet 5.5 (Low, Default Fallback) GDPval-AA34.1%
Artificial AnalysisClaude Sonnet 5.5 (Low, Default Fallback) CritPt11.4%
Artificial AnalysisClaude Sonnet 5.5 (Low, Default Fallback) SciCode49.1%
Artificial AnalysisClaude Sonnet 5.5 (Low, Default Fallback) Terminal-Bench 4.020.7%
Artificial AnalysisClaude Sonnet 5.5 (Low, Default Fallback) AA-Omniscience Accuracy46.0%
Artificial AnalysisClaude Sonnet 5.5 (Low, Default Fallback) AA-Omniscience Non-Hallucination Rate52.3%
Artificial AnalysisClaude Sonnet 5.5 (High, Default Fallback) Intelligence Index41.5
Artificial AnalysisClaude Sonnet 5.5 (High, Default Fallback) HLE45.8%
Artificial AnalysisClaude Sonnet 5.5 (High, Default Fallback) AA-LCR78.0%
Artificial AnalysisClaude Sonnet 5.5 (High, Default Fallback) GDPval-AA52.6%
Artificial AnalysisClaude Sonnet 5.5 (High, Default Fallback) CritPt24.6%
Artificial AnalysisClaude Sonnet 5.5 (High, Default Fallback) SciCode53.7%
Artificial AnalysisClaude Sonnet 5.5 (High, Default Fallback) Terminal-Bench 4.043.9%
Artificial AnalysisClaude Sonnet 5.5 (High, Default Fallback) AA-Omniscience Accuracy50.3%
Artificial AnalysisClaude Sonnet 5.5 (High, Default Fallback) AA-Omniscience Non-Hallucination Rate36.4%
Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) Intelligence Index54.5
Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) HLE55.0%
Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) AA-LCR82.7%
Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) GDPval-AA66.9%
Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) CritPt31.4%
Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) SciCode61.0%
Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) Terminal-Bench 4.063.6%
Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) AA-Omniscience Accuracy51.5%
Artificial AnalysisClaude Sonnet 5.5 (Max, Default Fallback) AA-Omniscience Non-Hallucination Rate56.7%
Artificial AnalysisClaude Sonnet 5.5 (Xhigh, Default Fallback) Intelligence Index49.9
Artificial AnalysisClaude Sonnet 5.5 (Xhigh, Default Fallback) HLE50.0%
Artificial AnalysisClaude Sonnet 5.5 (Xhigh, Default Fallback) AA-LCR79.7%
Artificial AnalysisClaude Sonnet 5.5 (Xhigh, Default Fallback) GDPval-AA62.1%
Artificial AnalysisClaude Sonnet 5.5 (Xhigh, Default Fallback) CritPt31.1%
Artificial AnalysisClaude Sonnet 5.5 (Xhigh, Default Fallback) SciCode57.3%
Artificial AnalysisClaude Sonnet 5.5 (Xhigh, Default Fallback) Terminal-Bench 4.057.1%
Artificial AnalysisClaude Sonnet 5.5 (Xhigh, Default Fallback) AA-Omniscience Accuracy50.9%
Artificial AnalysisClaude Sonnet 5.5 (Xhigh, Default Fallback) AA-Omniscience Non-Hallucination Rate38.3%
Artificial AnalysisClaude Sonnet 5.5 (Medium, Default Fallback) Intelligence Index30.8
Artificial AnalysisClaude Sonnet 5.5 (Medium, Default Fallback) HLE39.8%
Artificial AnalysisClaude Sonnet 5.5 (Medium, Default Fallback) AA-LCR76.3%
Artificial AnalysisClaude Sonnet 5.5 (Medium, Default Fallback) GDPval-AA41.3%
Artificial AnalysisClaude Sonnet 5.5 (Medium, Default Fallback) CritPt16.9%
Artificial AnalysisClaude Sonnet 5.5 (Medium, Default Fallback) SciCode52.9%
Artificial AnalysisClaude Sonnet 5.5 (Medium, Default Fallback) Terminal-Bench 4.029.8%
Artificial AnalysisClaude Sonnet 5.5 (Medium, Default Fallback) AA-Omniscience Accuracy45.8%
Artificial AnalysisClaude Sonnet 5.5 (Medium, Default Fallback) AA-Omniscience Non-Hallucination Rate50.0%
Design ArenaClaude Sonnet 5.5 Agents Arena Androidnative Elo1256
Design ArenaClaude Sonnet 5.5 Agents Arena Blender3d Elo1262
Design ArenaClaude Sonnet 5.5 Agents Arena Codetovideo Elo1314
Design ArenaClaude Sonnet 5.5 Agents Arena Mobile Apps Elo1259
Design ArenaClaude Sonnet 5.5 Agents Arena Pdf Elo1244
Design ArenaClaude Sonnet 5.5 Agents Arena Spreadsheet Elo1238
Design ArenaClaude Sonnet 5.5 Agents Arena Webapps Elo1295
Design ArenaClaude Sonnet 5.5 Models Arena 3D Elo1401
Design ArenaClaude Sonnet 5.5 Models Arena Code Categories Elo1346
Design ArenaClaude Sonnet 5.5 Models Arena Data Visualization Elo1359
Design ArenaClaude Sonnet 5.5 Models Arena Game Development Elo1385
Design ArenaClaude Sonnet 5.5 Models Arena SVG Elo1300
Design ArenaClaude Sonnet 5.5 Models Arena UI Component Elo1389
Design ArenaClaude Sonnet 5.5 Models Arena Website Elo1309
Vals AIClaude Sonnet 5.5 Access to Justice Benchmark74.9%
Vals AIClaude Sonnet 5.5 BioMysteryBench81.1%
Vals AIClaude Sonnet 5.5 ClaimBench100.0%
Vals AIClaude Sonnet 5.5 Code Migration v1.186.9%
Vals AIClaude Sonnet 5.5 CyberBench v1.159.6%
Vals AIClaude Sonnet 5.5 EMB v1.175.9%
Vals AIClaude Sonnet 5.5 Finance Agent v2.167.3%
Vals AIClaude Sonnet 5.5 Vals Finance Index64.5%
Vals AIClaude Sonnet 5.5 Financial Coaching Bench74.9%
Vals AIClaude Sonnet 5.5 HLAB-Vals-1.110.4%
Vals AIClaude Sonnet 5.5 Immigration69.0%
Vals AIClaude Sonnet 5.5 IOI83.1%
Vals AIClaude Sonnet 5.5 Vals Legal Index68.0%
Vals AIClaude Sonnet 5.5 Legal Research Bench48.1%
Vals AIClaude Sonnet 5.5 MedCode52.9%
Vals AIClaude Sonnet 5.5 MedScribe91.1%
Vals AIClaude Sonnet 5.5 MysteryMechanism49.1%
Vals AIClaude Sonnet 5.5 ProgramBench6.5%
Vals AIClaude Sonnet 5.5 ProofBench v1.1100.0%
Vals AIClaude Sonnet 5.5 Public Benefits Bench v1.167.2%
Vals AIClaude Sonnet 5.5 SAGE88.0%
Vals AIClaude Sonnet 5.5 Vals Science Index59.1%
Vals AIClaude Sonnet 5.5 SRE Bench30.2%
Vals AIClaude Sonnet 5.5 SWE-bench Multimodal58.3%
Vals AIClaude Sonnet 5.5 Tax Agent Bench42.0%
Vals AIClaude Sonnet 5.5 Terminal-Bench 4.064.1%
Vals AIClaude Sonnet 5.5 Terminal-Bench-Science47.1%
Vals AIClaude Sonnet 5.5 Vals Index70.9%
Vals AIClaude Sonnet 5.5 Vibe Code Bench v1.192.4%
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.
2.36Ttokens
2.
Descript
AI Video & Podcast Editor
699Btokens
3.
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.
683Btokens
4.
pi
There are many coding agents, but this one is yours.
236Btokens
5.
omp
new
181Btokens
Rest of OpenRouter
2.28B
Top 5 Apps
782M
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 Sonnet versions
Available through EU in-region routing
Anthropic: Claude Sonnet 5.5 is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).
Providers in EuropeAmazon Bedrock, Google VertexPrices in Europe
Amazon Bedrock: $2.20/M tokens input, $11/M tokens output
Google Vertex: $2.20/M tokens input, $11/M tokens output
Base URLhttps://eu.openrouter.ai/api/v1PlanRequires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing
Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs
Documentation
Guides, cookbooks, blog posts, and tools for building with Anthropic: Claude Sonnet 5.5 on OpenRouter.
Claude 5.5 Migration GuideCookbook
Reranking in RAG: How to Fix Bad Retrieval with a RerankerBlog post
How to Benchmark LLMsBlog post
MCP vs CLI vs Skills: What Each Costs in ContextBlog post
Build an AI Code Reviewer with OpenRouterBlog post
Claude Opus vs Sonnet vs Haiku: Which Should You Use?Blog post
How Much Does Claude Code Cost? Real Session Costs by ModelBlog post
Hit Your Claude Code Usage Limit? How to Keep CodingBlog post
Claude 529 Overloaded: What It Means and How to Fix ItBlog post
Frequently asked questions
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.
The Claude Sonnet 5.5 documentation on OpenRouter includes the Claude 5.5 Migration Guide cookbook, the Reranking in RAG: How to Fix Bad Retrieval with a Reranker blog post, the How to Benchmark LLMs blog post, the MCP vs CLI vs Skills: What Each Costs in Context blog post, the Build an AI Code Reviewer with OpenRouter blog post, the Claude Opus vs Sonnet vs Haiku: Which Should You Use? blog post, the How Much Does Claude Code Cost? Real Session Costs by Model blog post, the Hit Your Claude Code Usage Limit? How to Keep Coding blog post, and the Claude 529 Overloaded: What It Means and How to Fix It blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.
Claude Sonnet 5.5 costs $2.00/M input tokens and $10.00/M output tokens, with separate rates for Cache Read at $0.10/M tokens, Cache Write at $2.50/M tokens, and Cache Write (1h) at $4.00/M tokens.
Claude Sonnet 5.5 has a 1,000,000 token context window. It supports up to 128,000 completion tokens.
Yes. Claude Sonnet 5.5 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Claude Sonnet 5.5 accepts text, images, and files such as PDFs as input and returns text.
Claude Sonnet 5.5 is served by 5 providers on OpenRouter: Google Vertex, Amazon Bedrock, Azure, Claude Platform on AWS, 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 Sonnet 5.5 was released on September 28, 2026.
正文以来源语言显示。