Claude Sonnet 5.5

Anthropic's balance of speed and intelligence, with a 1,000,000-token context window at $2 input and $10 output per 1M tokens.

Anthropic describes it as
“The best combination of speed and intelligence”

Compare this model Check how your prompt fits this model’s context window

Last verified: Oct 31, 2026

Context window: 1,000,000
Max output: 128,000
Input price: $2.00
Output price: $10.00
Extended output (Batch API (beta)): 300,000
Released: Sep 28, 2026
Knowledge cutoff: Jun 2026
API model ID: claude-sonnet-5-5

Batch API (beta): Message Batches API only, with the output-300k-2026-03-24 beta header. Synchronous requests are limited to 128,000 output tokens.
Anthropic's pages list a context window and a maximum output but do not state a separate maximum-input figure.

About Claude Sonnet 5.5

Claude Sonnet 5.5 is described by Anthropic as the best combination of speed and intelligence. It has a 1,000,000-token context window and up to 128,000 output tokens, takes text, image and PDF input, and is priced at $2 input and $10 output per million tokens with the full 1M context at standard pricing.

API pricing

Per-token API prices from the provider's pricing page. Thresholds and processing modes are shown explicitly, not folded into one number.

Standard processing · USD per 1M tokens
Rate	Price
Input	$2.00
Cached input	$0.10
Output	$10.00
Cache write (5 minutes)	$2.50
Cache write (1 hour)	$4.00

Batch processing · USD per 1M tokens
Rate	Price
Input	$1.00
Output	$5.00

Cache write prices are shown for 5-minute and 1-hour retention.
Setting inference_geo to "us" applies a 1.1x multiplier on Claude 4.6 and later models.
Anthropic includes the full 1M-token context window at standard pricing for this model.

Modalities and capabilities

What the provider documents for this model. “API tool” means it needs a provider tool or endpoint rather than being native to the model.

Input modalities: Text, Image, PDF
Output modalities: Text

ReasoningReasoning: ✓ Yes
Adaptive thinking. The lowest setting is between_tools, which turns off up-front thinking.
Tool / function callingTool / function calling: ✓ Yes
Structured outputsStructured outputs: ✓ Yes
Web searchWeb search: ✓ Yes · API tool
Web search tool.
Code executionCode execution: ✓ Yes · API tool
Code execution tool.
Computer useComputer use: ✓ Yes · API tool
On the Claude API, through computer_toolset_20260801.
Image generationImage generation: ✕ No
Output is text only.
Prompt cachingPrompt caching: ✓ Yes
Minimum cacheable prompt length is 512 tokens.
Batch APIBatch API: ✓ Yes

Benchmarks

Individual named benchmarks only: there is no overall score. Vendor-reported results come from the model maker's own launch materials. Scores from different sources, versions or settings are not directly comparable.

Benchmark results for Claude Sonnet 5.5
Benchmark	Score	Source type	Reported by
AA-Briefcase (v1.1)	1811	Vendor-reported	AnthropicSep 28, 2026
CursorBench (v4.0)	55.5%	Vendor-reported	AnthropicSep 28, 2026
FrontierCode (v1.1, Main)Setting: xhigh effortAnthropic's Sonnet 5.5 page reports 46.2% at max effort, where it says the model scores lower.	52.1%	Vendor-reported	Anthropic (reference column on the Haiku 5.5 page)Oct 7, 2026
GDPval-AA (v2.1)	1844	Vendor-reported	AnthropicSep 28, 2026
Humanity's Last Exam (with tools)	64.5%	Vendor-reported	AnthropicSep 28, 2026
OSWorld (v2.1, partial credit)	80.1%	Vendor-reported	AnthropicSep 28, 2026
Terminal-Bench (v4.0)	70.6%	Vendor-reported	AnthropicSep 28, 2026

Availability and API identifiers

Where Claude Sonnet 5.5 is available and the identifier used there
Surface	Identifier
Claude APIEvery Claude model ID is a pinned snapshot; there is no separate dated ID.	claude-sonnet-5-5
Amazon Bedrock	anthropic.claude-sonnet-5-5
Google Cloud (Google-managed and Anthropic-managed)	claude-sonnet-5-5
Microsoft Foundry	claude-sonnet-5-5
Claude Platform on AWS	claude-sonnet-5-5

Limitations and caveats

API vs. apps. These limits and prices describe the Claude API model. The Claude apps can apply different limits and are billed through subscriptions, not per token.

Anthropic lists retirement as not sooner than September 28, 2027.
Anthropic says Claude 4.7 and later models produce approximately 30% more tokens for the same text than earlier Claude models.
Setting temperature, top_p or top_k returns a 400 error, per Anthropic's page.
Forced tool use returns an error.
Artificial Analysis ran GDPval-AA and AA-Briefcase on a pre-release deployment with a structured-outputs bug; Anthropic expects the effect on Sonnet 5.5's scores to be small and to understate them.

Sources

Last verified against these sources on Oct 31, 2026. Prices and limits change; follow the links for the live figure.

Anthropic docs — Claude Sonnet 5.5
Supports: status, release date, knowledge cutoff, context window, max output, modalities, pricing
OfficialChecked Oct 31, 2026
Anthropic docs — Models overview
Supports: status, context window, max output, modalities, capabilities
OfficialChecked Oct 31, 2026
Anthropic docs — Pricing
Supports: pricing
OfficialChecked Oct 31, 2026
Anthropic docs — Structured outputs
Supports: capabilities
OfficialChecked Oct 31, 2026
Anthropic docs — Web search tool
Supports: capabilities
OfficialChecked Oct 31, 2026
Anthropic docs — Computer use tool
Supports: capabilities
OfficialChecked Oct 31, 2026
Anthropic docs — Code execution tool
Supports: capabilities
OfficialChecked Oct 31, 2026
Anthropic docs — PDF support
Supports: modalities, capabilities
OfficialChecked Oct 31, 2026
Anthropic docs — Prompt caching
Supports: capabilities
OfficialChecked Oct 31, 2026
Anthropic docs — Batch processing
Supports: capabilities
OfficialChecked Oct 31, 2026
Anthropic — Claude Sonnet 5.5 launch page
Supports: benchmarks
Anthropic launch page; scores are Anthropic-reported.
Vendor benchmarkChecked Oct 31, 2026
Anthropic — Claude Haiku 5.5 launch page
Supports: benchmarks
Anthropic launch page; scores are Anthropic-reported.
Vendor benchmarkChecked Oct 31, 2026

Key facts