For Developers/Models/Claude Sonnet 5.5
Closed SourceAnthropicReleased 2026-09

Claude Sonnet 5.5

Faster, cheaper mid-tier model for everyday tasks and agentic work

Context window

1M

Input / 1M tokens

$2.00

Output / 1M tokens

$10.00

Provider

Anthropic

Data verified 2026-09-29

Claude Sonnet 5.5 is Anthropic's mid-tier model designed for everyday tasks, coding, and document production. It runs 30% faster than Sonnet 5 while maintaining the same list price. The model scores nearly as well as Opus 5.5 on many benchmarks while offering better speed and cost efficiency for well-scoped work.

Capability index

Relative estimates (0-100) to place this model against its peers, grounded in published benchmarks.

Coding
80
Reasoning
70
Math
72
Multimodal
75
Long context
85
Speed
90
Cost efficiency
85

How to access it

Available via Anthropic Claude API, Amazon Web Services, Google Cloud, and Microsoft Azure with standard API access.

Strengths

  • ✓30% faster execution than Sonnet 5
  • ✓Strong agentic coding performance
  • ✓Excellent at document generation and formatting
  • ✓Design-oriented capabilities
  • ✓Same price as Sonnet 5

Best for developers who...

Everyday tasks and workflowsAgentic coding and automationDocument, slide, and spreadsheet creationBug fixing and code refinementHigh-volume applications

When to choose it (and when not to)

Reach for Claude Sonnet 5.5 when...

  • →Need faster responses than Sonnet 5
  • →Working with well-scoped tasks
  • →Cost-conscious deployment at scale
  • →Agentic applications

Look elsewhere if...

  • ✕Complex reasoning requiring sustained judgment
  • ✕Open-ended problems needing careful analysis
  • ✕Tasks where Opus 5.5 is necessary

How to use it

  • ›Use between_tools setting for production deployments
  • ›Structure prompts around well-defined task boundaries
  • ›Leverage its speed for high-volume agentic loops

Quickstart

Python
from anthropic import Anthropic
client = Anthropic()
message = client.messages.create(
  model="claude-sonnet-5-5",
  max_tokens=1024,
  messages=[{"role": "user", "content": "Hello!"}]
)
print(message.content[0].text)

Use model ID 'claude-sonnet-5-5' with Anthropic SDK

API model id: claude-sonnet-5-5

Benchmarks

BenchmarkScoreNotes
Terminal-Bench 4.0 (Agentic Coding)70.6%Significant improvement over Sonnet 5's 10.3%
CursorBench 4.055.5%vs 34.1% for Sonnet 5
GDPval-AA v2.1 (Knowledge Work)1844 EloTwo points behind Opus 5.5's 1846

Source: Anthropic official announcement

Compare Claude Sonnet 5.5

Compare Claude Sonnet 5.5 with any other model

Build a comparison →
All model comparisons →

Learn the concepts