Where is the Claude Sonnet 5.5 documentation?

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.

How much does Claude Sonnet 5.5 cost?

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.

What is the context length of Claude Sonnet 5.5?

Claude Sonnet 5.5 has a 1,000,000 token context window. It supports up to 128,000 completion tokens.

Does Claude Sonnet 5.5 support tool calling and structured outputs?

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.

What inputs and outputs does Claude Sonnet 5.5 support?

Claude Sonnet 5.5 accepts text, images, and files such as PDFs as input and returns text.

Which providers serve Claude Sonnet 5.5?

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.

When was Claude Sonnet 5.5 released?

Claude Sonnet 5.5 was released on September 28, 2026.

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

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	$0.10	1.86s	111 tok/s	99.97%
	$2.00	$10.00	$0.10	1.68s	112 tok/s	100.00%
	$2.00	$10.00	$0.10	1.31s	121 tok/s	99.21%
	$2.00	$10.00	$0.10	1.92s	93 tok/s	100.00%
	$2.00	$10.00	$0.10	1.52s	98 tok/s	99.04%
Not used in Standard routing:Why these endpoints are not used
	$2.20	$11.00	$0.11	0.59s	99 tok/s	100.00%
	$2.20	$11.00	$0.11	2.45s	75 tok/s	100.00%
	$2.20	$11.00	$0.11	1.45s	111 tok/s	100.00%
	$2.20	$11.00	$0.11	1.53s	90 tok/s	98.61%
	$2.20	$11.00	$0.11	0.94s	103 tok/s	100.00%

Input $2.00Output $10.00
111 tok/s99.97% uptime
Input $2.00Output $10.00
112 tok/s100.00% uptime
Input $2.00Output $10.00
121 tok/s99.21% uptime
Input $2.00Output $10.00
93 tok/s100.00% uptime
Input $2.00Output $10.00
98 tok/s99.04% uptime
Not used in Standard routing:Why these endpoints are not used
Input $2.20Output $11.00
99 tok/s100.00% uptime
Input $2.20Output $11.00
75 tok/s100.00% uptime
Input $2.20Output $11.00
111 tok/s100.00% uptime
Input $2.20Output $11.00
90 tok/s98.61% uptime
Input $2.20Output $11.00
103 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

$0.5377/M tokens

Output

$10.02/M tokens

Claude Sonnet 5.5 — Price history

Price history

No effective price data for this selection

	$0.427	$10.00	85.6%	20.3%
	$0.517	$10.00	80.8%	34.9%
	$0.528	$10.00	80.7%	16.5%
	$0.641	$10.00	78.9%	22.4%
	$0.975	$10.00	58.6%	1.8%
Not used in Standard routing:Why these endpoints are not used
	$0.386	$11.00	91.4%	0.4%
	$0.547	$11.00	85.0%	2.4%
	$0.561	$11.00	81.4%	1.2%
	$0.600	$11.00	78.7%	0.0%
	$0.956	$11.00	70.6%	0.1%

Effective in $0.427Effective out $10.00
Token share
20.3%
Effective in $0.517Effective out $10.00
Token share
34.9%
Effective in $0.528Effective out $10.00
Token share
16.5%
Effective in $0.641Effective out $10.00
Token share
22.4%
Effective in $0.975Effective out $10.00
Token share
1.8%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.386Effective out $11.00
Token share
0.4%
Effective in $0.547Effective out $11.00
Token share
2.4%
Effective in $0.561Effective out $11.00
Token share
1.2%
Effective in $0.600Effective out $11.00
Token share
0.0%
Effective in $0.956Effective out $11.00
Token share
0.1%

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

121tok/s

P50, best across providers

Latency

0.59s

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)

100.00%

Availability (3d)

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

99.83%

Without Routing

97.41%

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)
Source	Benchmark	Score
Artificial Analysis	Claude Sonnet 5.5 (Low, Default Fallback) Intelligence Index	25.6
Artificial Analysis	Claude Sonnet 5.5 (Low, Default Fallback) HLE	36.2%
Artificial Analysis	Claude Sonnet 5.5 (Low, Default Fallback) AA-LCR	76.0%
Artificial Analysis	Claude Sonnet 5.5 (Low, Default Fallback) GDPval-AA	34.1%
Artificial Analysis	Claude Sonnet 5.5 (Low, Default Fallback) CritPt	11.4%
Artificial Analysis	Claude Sonnet 5.5 (Low, Default Fallback) SciCode	49.1%
Artificial Analysis	Claude Sonnet 5.5 (Low, Default Fallback) Terminal-Bench 4.0	20.7%
Artificial Analysis	Claude Sonnet 5.5 (Low, Default Fallback) AA-Omniscience Accuracy	46.0%
Artificial Analysis	Claude Sonnet 5.5 (Low, Default Fallback) AA-Omniscience Non-Hallucination Rate	52.3%
Artificial Analysis	Claude Sonnet 5.5 (Medium, Default Fallback) Intelligence Index	30.8
Artificial Analysis	Claude Sonnet 5.5 (Medium, Default Fallback) HLE	39.8%
Artificial Analysis	Claude Sonnet 5.5 (Medium, Default Fallback) AA-LCR	76.3%
Artificial Analysis	Claude Sonnet 5.5 (Medium, Default Fallback) GDPval-AA	41.4%
Artificial Analysis	Claude Sonnet 5.5 (Medium, Default Fallback) CritPt	16.9%
Artificial Analysis	Claude Sonnet 5.5 (Medium, Default Fallback) SciCode	52.9%
Artificial Analysis	Claude Sonnet 5.5 (Medium, Default Fallback) Terminal-Bench 4.0	29.8%
Artificial Analysis	Claude Sonnet 5.5 (Medium, Default Fallback) AA-Omniscience Accuracy	45.8%
Artificial Analysis	Claude Sonnet 5.5 (Medium, Default Fallback) AA-Omniscience Non-Hallucination Rate	50.0%
Artificial Analysis	Claude Sonnet 5.5 (Max, Default Fallback) Intelligence Index	54.5
Artificial Analysis	Claude Sonnet 5.5 (Max, Default Fallback) HLE	55.0%
Artificial Analysis	Claude Sonnet 5.5 (Max, Default Fallback) AA-LCR	82.7%
Artificial Analysis	Claude Sonnet 5.5 (Max, Default Fallback) GDPval-AA	66.9%
Artificial Analysis	Claude Sonnet 5.5 (Max, Default Fallback) CritPt	31.4%
Artificial Analysis	Claude Sonnet 5.5 (Max, Default Fallback) SciCode	61.0%
Artificial Analysis	Claude Sonnet 5.5 (Max, Default Fallback) Terminal-Bench 4.0	63.6%
Artificial Analysis	Claude Sonnet 5.5 (Max, Default Fallback) AA-Omniscience Accuracy	51.5%
Artificial Analysis	Claude Sonnet 5.5 (Max, Default Fallback) AA-Omniscience Non-Hallucination Rate	56.7%
Artificial Analysis	Claude Sonnet 5.5 (Xhigh, Default Fallback) Intelligence Index	49.9
Artificial Analysis	Claude Sonnet 5.5 (Xhigh, Default Fallback) HLE	50.0%
Artificial Analysis	Claude Sonnet 5.5 (Xhigh, Default Fallback) AA-LCR	79.7%
Artificial Analysis	Claude Sonnet 5.5 (Xhigh, Default Fallback) GDPval-AA	61.8%
Artificial Analysis	Claude Sonnet 5.5 (Xhigh, Default Fallback) CritPt	31.1%
Artificial Analysis	Claude Sonnet 5.5 (Xhigh, Default Fallback) SciCode	57.3%
Artificial Analysis	Claude Sonnet 5.5 (Xhigh, Default Fallback) Terminal-Bench 4.0	57.1%
Artificial Analysis	Claude Sonnet 5.5 (Xhigh, Default Fallback) AA-Omniscience Accuracy	50.9%
Artificial Analysis	Claude Sonnet 5.5 (Xhigh, Default Fallback) AA-Omniscience Non-Hallucination Rate	38.3%
Artificial Analysis	Claude Sonnet 5.5 (High, Default Fallback) Intelligence Index	41.5
Artificial Analysis	Claude Sonnet 5.5 (High, Default Fallback) HLE	45.8%
Artificial Analysis	Claude Sonnet 5.5 (High, Default Fallback) AA-LCR	78.0%
Artificial Analysis	Claude Sonnet 5.5 (High, Default Fallback) GDPval-AA	52.8%
Artificial Analysis	Claude Sonnet 5.5 (High, Default Fallback) CritPt	24.6%
Artificial Analysis	Claude Sonnet 5.5 (High, Default Fallback) SciCode	53.7%
Artificial Analysis	Claude Sonnet 5.5 (High, Default Fallback) Terminal-Bench 4.0	43.9%
Artificial Analysis	Claude Sonnet 5.5 (High, Default Fallback) AA-Omniscience Accuracy	50.3%
Artificial Analysis	Claude Sonnet 5.5 (High, Default Fallback) AA-Omniscience Non-Hallucination Rate	36.4%
Design Arena	Claude Sonnet 5.5 Agents Arena Androidnative Elo	1260
Design Arena	Claude Sonnet 5.5 Agents Arena Blender3d Elo	1268
Design Arena	Claude Sonnet 5.5 Agents Arena Codetovideo Elo	1316
Design Arena	Claude Sonnet 5.5 Agents Arena Mobile Apps Elo	1261
Design Arena	Claude Sonnet 5.5 Agents Arena Pdf Elo	1237
Design Arena	Claude Sonnet 5.5 Agents Arena Spreadsheet Elo	1281
Design Arena	Claude Sonnet 5.5 Agents Arena Webapps Elo	1280
Design Arena	Claude Sonnet 5.5 Models Arena 3D Elo	1397
Design Arena	Claude Sonnet 5.5 Models Arena Code Categories Elo	1345
Design Arena	Claude Sonnet 5.5 Models Arena Data Visualization Elo	1360
Design Arena	Claude Sonnet 5.5 Models Arena Game Development Elo	1388
Design Arena	Claude Sonnet 5.5 Models Arena SVG Elo	1299
Design Arena	Claude Sonnet 5.5 Models Arena UI Component Elo	1388
Design Arena	Claude Sonnet 5.5 Models Arena Website Elo	1309
Vals AI	Claude Sonnet 5.5 Access to Justice Benchmark	74.9%
Vals AI	Claude Sonnet 5.5 BioMysteryBench	81.1%
Vals AI	Claude Sonnet 5.5 ClaimBench	100.0%
Vals AI	Claude Sonnet 5.5 Code Migration v1.1	86.9%
Vals AI	Claude Sonnet 5.5 CyberBench v1.1	59.6%
Vals AI	Claude Sonnet 5.5 EMB v1.1	75.9%
Vals AI	Claude Sonnet 5.5 Finance Agent v2.1	67.3%
Vals AI	Claude Sonnet 5.5 Vals Finance Index	64.5%
Vals AI	Claude Sonnet 5.5 Financial Coaching Bench	74.9%
Vals AI	Claude Sonnet 5.5 HLAB-Vals-1.1	10.4%
Vals AI	Claude Sonnet 5.5 Immigration	69.0%
Vals AI	Claude Sonnet 5.5 IOI	83.1%
Vals AI	Claude Sonnet 5.5 Vals Legal Index	68.0%
Vals AI	Claude Sonnet 5.5 Legal Research Bench	48.1%
Vals AI	Claude Sonnet 5.5 MedCode	52.9%
Vals AI	Claude Sonnet 5.5 MedScribe	91.1%
Vals AI	Claude Sonnet 5.5 MysteryMechanism	49.1%
Vals AI	Claude Sonnet 5.5 ProgramBench	6.5%
Vals AI	Claude Sonnet 5.5 ProofBench v1.1	100.0%
Vals AI	Claude Sonnet 5.5 Public Benefits Bench v1.1	67.2%
Vals AI	Claude Sonnet 5.5 SAGE	88.0%
Vals AI	Claude Sonnet 5.5 Vals Science Index	59.1%
Vals AI	Claude Sonnet 5.5 SRE Bench	30.2%
Vals AI	Claude Sonnet 5.5 SWE-bench Multimodal	58.3%
Vals AI	Claude Sonnet 5.5 Tax Agent Bench	42.0%
Vals AI	Claude Sonnet 5.5 Terminal-Bench 4.0	64.1%
Vals AI	Claude Sonnet 5.5 Terminal-Bench-Science	47.1%
Vals AI	Claude Sonnet 5.5 Vals Index	70.9%
Vals AI	Claude Sonnet 5.5 Vibe Code Bench v1.1	92.4%

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.

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.

2.62Ttokens

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.

716Btokens

Descript

AI Video & Podcast Editor

709Btokens

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

199Btokens

omp

new

188Btokens

Rest of OpenRouter

209B

Top 5 Apps

121B

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 Europe

Amazon Bedrock, Google Vertex

Prices 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 URL

https://eu.openrouter.ai/api/v1

Plan

Requires 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

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 (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

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.

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

Claude Opus 4.8 (batch)

Text1M context$2.50 / $12.50

Anthropic: Claude Sonnet 5.5

Providers