Home/Models
Models/Anthropic

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.

anthropic/claude-sonnet-5-5
Organization
Anthropic
Family
claude-sonnet
Providers
24
Context
1,000,000
Output limit
128,000
Knowledge
2026-06
Release
2026-09-28
Updated
2026-09-28
Weights
Closed
Input
text, image, pdf
Output
text
Capabilities
Tools, Reasoning

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

39 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
302.AI
claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYes—
View
Amazon Bedrock
us.anthropic.claude-sonnet-5-5
1,000,000128,000$2.20 / $11.00YesYesNo
View
Amazon Bedrock
anthropic.claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesNo
View
Amazon Bedrock
eu.anthropic.claude-sonnet-5-5
1,000,000128,000$2.20 / $11.00YesYesNo
View
Amazon Bedrock
global.anthropic.claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesNo
View
Anthropic
claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesYes
View
Azure
claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesYes
View
Azure Cognitive Services
claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesYes
View
CrossModel
anthropic/claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYes—
View
DevPass (LLM Gateway)
claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYes—
View
DigitalOcean
anthropic-claude-sonnet-5.5
1,000,000128,000$2.00 / $10.00YesYes—
View
Eden AI
anthropic/claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesYes
View
Eden AI
anthropic/claude-sonnet-latest
1,000,000128,000$2.00 / $10.00YesYesYes
View
GitHub Copilot
claude-sonnet-5.5
1,000,000128,000$2.00 / $10.00YesYes—
View
GitLab Duo
duo-chat-sonnet-5-5
1,000,00064,000$0.00 / $0.00YesYes—
View
Kilo Gateway
anthropic/claude-sonnet-5.5
1,000,000128,000$2.00 / $10.00YesYesYes
View
LLM Gateway
aws-bedrock/claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesNo
View
LLM Gateway
azure-anthropic/claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesYes
View
LLM Gateway
anthropic/claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesYes
View
Merge Gateway
anthropic/claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesYes
View
NanoGPT
anthropic/claude-sonnet-5.5:thinking
1,000,000128,000$2.00 / $10.00YesYesYes
View
NanoGPT
anthropic/claude-sonnet-5.5
1,000,000128,000$2.00 / $10.00YesYesYes
View
Ofox
anthropic/claude-sonnet-5.5
1,000,000128,000$2.00 / $10.00YesYes—
View
OpenCode Zen
claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYes—
View
Amazon Bedrockvia OpenRouter
anthropic/claude-sonnet-5.5
unknown		1,000,000128,000$2.00 / $10.00YesYesNo
View
Anthropicvia OpenRouter
anthropic/claude-sonnet-5.5
unknown		1,000,000128,000$2.00 / $10.00YesYesYes
View
Azurevia OpenRouter
anthropic/claude-sonnet-5.5
unknown		1,000,000128,000$2.20 / $11.00YesYesYes
View
Azurevia OpenRouter
anthropic/claude-sonnet-5.5
unknown		1,000,000128,000$2.00 / $10.00YesYesYes
View
Claude Platform on AWSvia OpenRouter
anthropic/claude-sonnet-5.5
unknown		1,000,000128,000$2.00 / $10.00YesYesNo
View
Googlevia OpenRouter
anthropic/claude-sonnet-5.5
unknown		1,000,000128,000$2.20 / $11.00YesYesYes
View
Googlevia OpenRouter
anthropic/claude-sonnet-5.5
unknown		1,000,000128,000$2.20 / $11.00YesYesYes
View
Googlevia OpenRouter
anthropic/claude-sonnet-5.5
unknown		1,000,000128,000$2.00 / $10.00YesYesYes
View
Requesty
claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesYes
View
Requesty
claude-sonnet-5-5@eu
1,000,000128,000$2.20 / $11.00YesYesYes
View
Venice AI
claude-sonnet-5-5
1,000,000128,000$2.50 / $12.50YesYesYes
View
Vercel AI Gateway
anthropic/claude-sonnet-5.5
1,000,000128,000$2.00 / $10.00YesYes—
View
Vertex
claude-sonnet-5-5@default
1,000,000128,000$2.00 / $10.00YesYesYes
View
Vertex (Anthropic)
claude-sonnet-5-5@default
1,000,000128,000$2.00 / $10.00YesYesYes
View
Vivgrid
claude-sonnet-5-5
1,000,000128,000$2.00 / $10.00YesYesYes
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.00Per 1M input tokens
Output from$0.00Per 1M output tokens
Available offers39Across 24 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 8 lowest-priced configurations
InputOutput
Amazon Bedrockamazon-bedrock
$2.00$10.00
Anthropicanthropic
$2.00$10.00
Azureazure/global
$2.00$10.00
Claude Platform on AWSclaude-on-aws
$2.00$10.00
Googlegoogle-vertex/global
$2.00$10.00
Azureazure/us
$2.20$11.00
Googlegoogle-vertex/europe
$2.20$11.00
Googlegoogle-vertex/us
$2.20$11.00
anthropic/claude-sonnet-5.5Observed
Input
$2.00
Output
$10.00
Cache read
$0.20
Cache write
$2.50
Cache write · 1 hour
$4.00
Additional fees and pricing conditions
web search
$0.01 / search
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Amazon Bedrockamazon-bedrock$2.00$10.00$0.20$2.50
Anthropicanthropic$2.00$10.00$0.20$2.50
Azureazure/us$2.20$11.00$0.22$2.75
Azureazure/global$2.00$10.00$0.20$2.50
Claude Platform on AWSclaude-on-aws$2.00$10.00$0.20$2.50
Googlegoogle-vertex/europe$2.20$11.00$0.22$2.75
Googlegoogle-vertex/us$2.20$11.00$0.22$2.75
Googlegoogle-vertex/global$2.00$10.00$0.20$2.50

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock
1,265–8,688.8 ms
Anthropicanthropic
1,511.5–8,271.69 ms
Azureazure/us
1,371–3,467.37 ms
Azureazure/global
859–5,194.27 ms
Claude Platform on AWSclaude-on-aws
1,859.5–11,485.45 ms
Googlegoogle-vertex/europe
848–3,824.27 ms
All latency percentiles 8 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock1,265 ms2,958 ms4,125 ms8,688.8 ms
Anthropicanthropic1,511.5 ms3,078.25 ms4,000 ms8,271.69 ms
Azureazure/us1,371 ms2,834.5 ms3,461.7 ms3,467.37 ms
Azureazure/global859 ms1,464 ms2,594 ms5,194.27 ms
Claude Platform on AWSclaude-on-aws1,859.5 ms3,409 ms4,919.4 ms11,485.45 ms
Googlegoogle-vertex/europe848 ms1,554.25 ms2,437.7 ms3,824.27 ms
Googlegoogle-vertex/us1,276.5 ms1,837.75 ms2,082 ms2,143.2 ms
Googlegoogle-vertex/global2,473 ms4,120.75 ms6,602.5 ms16,995.45 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock
85–189 t/s
Anthropicanthropic
67–183 t/s
Azureazure/us
72–108.58 t/s
Azureazure/global
54–180 t/s
Claude Platform on AWSclaude-on-aws
82–188 t/s
Googlegoogle-vertex/europe
88–179 t/s
All throughput percentiles 8 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock85 t/s108 t/s140 t/s189 t/s
Anthropicanthropic67 t/s106 t/s129 t/s183 t/s
Azureazure/us72 t/s96.5 t/s104.8 t/s108.58 t/s
Azureazure/global54 t/s107 t/s130 t/s180 t/s
Claude Platform on AWSclaude-on-aws82 t/s112 t/s142 t/s188 t/s
Googlegoogle-vertex/europe88 t/s107 t/s128 t/s179 t/s
Googlegoogle-vertex/us102 t/s179.5 t/s182.2 t/s183.82 t/s
Googlegoogle-vertex/global95 t/s128 t/s165 t/s213 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 8 endpoints
Endpoint5 minutes30 minutes24 hours
Amazon Bedrockamazon-bedrock
Anthropicanthropic
Azureazure/us
Azureazure/global
Claude Platform on AWSclaude-on-aws
Googlegoogle-vertex/europe
Googlegoogle-vertex/us
Googlegoogle-vertex/global

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations
anthropic/claude-sonnet-5.5Observed
Benchmark profileArtificial Analysis · shared source scale from 0 to 60
Intelligence56
Design ArenaCategoryEloWin rateRank
modelsuicomponent1,41568.4%1

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
gpqa diamondAnthropic: Claude Sonnet 5.5
92.088%
tau bench verified airlineAnthropic: Claude Sonnet 5.5
74.667%
EvaluationConfigurationSourceResultsDetails
models · uicomponentClaude Sonnet 5.5anthropic/claude-sonnet-5.5-20260928Design Arena1,415 Elo
Details
Composite indicesClaude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)anthropic/claude-sonnet-5.5-20260928Artificial AnalysisIntelligence 56 · Coding — · Agentic —
Details
gpqa diamondAnthropic: Claude Sonnet 5.5anthropic/claude-sonnet-5.5-20260928OpenRouter92.088%
Details
tau bench verified airlineAnthropic: Claude Sonnet 5.5anthropic/claude-sonnet-5.5-20260928OpenRouter74.667%
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days
Daily token usage661,163,452,651 reported tokens · 5 days with observations
Jul 6, 2026Oct 3, 2026
Daily observations · 5 days
Date (UTC)Reported tokensReported routes
Oct 3, 2026129,983,524,9791
Oct 2, 2026141,082,047,7831
Oct 1, 2026153,186,607,5801
Sep 30, 2026138,238,390,6471
Sep 29, 202698,672,881,6621

Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
anthropic/claude-sonnet-5.5Observed
Context
1,000,000
Maximum output
128,000
Tokenizer
Claude
Input
text, image, file
Output
text
Moderation
Yes
Added to OpenRouter
2026-09-28
Base URLhttps://openrouter.ai/api/v1
Model IDanthropic/claude-sonnet-5.5
Version IDanthropic/claude-sonnet-5.5-20260928

Reasoning

Required
Yes
Enabled by default
Not reported
Default effort
high
Supported efforts
max, xhigh, high, medium, low

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • reasoning_effort
  • response_format
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • verbosity

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Claude Sonnet 5.5 cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Claude Sonnet 5.5?

There are 39 cataloged offers across 24 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,000,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Catalog history · 1 recorded revision

Metadata observations since this model was first cataloged. These are not model release versions.

  • · 9d0ae8b7bbce