Claude Sonnet 5.5
Claude Sonnet 5.5 is Anthropic's September 28, 2026 Sonnet model, documented as a clear upgrade over Claude Sonnet 5 that runs more than 30% faster and costs up to 30% less for most work.
Provider
Anthropic
Model family
Anthropic Claude
Multimodal LLM
Cost tier
Sonnet
Status
Current
Release Sep 28, 2026
Why teams choose it
Anthropic says Sonnet 5.5 is the complement to Opus 5.5: use Opus 5.5 for the hardest
long-running work and Sonnet 5.5 for most production tasks.
5-minute cache writes are $2.50, 1-hour cache writes are $4, and cache reads are $0.20 per million tokens
Batch is 50% off input and output.
The lowest adaptive-thinking setting is between_tools, which turns off up-front thinking and works at high effort or below
Retirement is not sooner than September 28, 2027
Platform IDs include Bedrock anthropic.claude-sonnet-5-5, plus Google Cloud, Foundry, and Claude Platform on AWS.
Tradeoffs to know
- Forced tool use errors, and thinking blocks are tied to the model and conversation. computer_20251124 is rejected on the Claude API and Google Cloud.
- The advisor tool rejects Opus 4.8, Opus 4.7, and Sonnet 5 as advisors. Non-default temperature, top_p, or top_k returns HTTP 400.
- Synchronous output is 128K tokens. 300K batch output needs the output-300k-2026-03-24 beta header. Minimum cacheable prompt is 512 tokens.
Technical specs
- Inputs
- text, image
- Outputs
- text
- Capabilities
- agentic coding, adaptive thinking, tool use, vision, long context
- License
- Proprietary API
- Source
- https://platform.claude.com/docs/en/models/sonnet-5-5/overview
- Latency
- Fast
- Context tokens
- 1,000,000
- Knowledge Cutoff
- 2026-06
- Max output tokens
- 128,000
- Input Usd Per Million
- 2
- Output Usd Per Million
- 10
- Cache Read Usd Per Million
- 0.2
- Cache Write 1h Usd Per Million
- 4
- Cache Write 5m Usd Per Million
- 2.5
Benchmarks
No independent or vendor benchmark scores in this catalog entry.
Anthropic Claude family lineup
Current models
Previous versions
Related models
Claude Sonnet 5.5 FAQ
What is Claude Sonnet 5.5?
Claude Sonnet 5.5 is Anthropic's September 28, 2026 Sonnet model, documented as a clear upgrade over Claude Sonnet 5 that runs more than 30% faster and costs up to 30% less for most work. The Claude API ID is claude-sonnet-5-5. It has a 1M-token context window, 128K synchronous max output, text and image input, text output, adaptive thinking, and default effort high. Standard price is $2 input and $10 output per million tokens.
When does Claude Sonnet 5.5 fit best?
Production coding agents
What should teams watch out for with Claude Sonnet 5.5?
Forced tool use errors, and thinking blocks are tied to the model and conversation. computer_20251124 is rejected on the Claude API and Google Cloud.
Explore next
Models, tools, and comparisons that connect to this reference.