Claude Sonnet 5
Language modelPrevious generationCard summarizedBuilt to be the most agentic Sonnet model yet
Active (legacy) · retires not before 30 Jun 2027● Re-checked 12 Oct 2026 · 108 facts · 0 corrections · 2 unconfirmedSource: System Card: Claude Sonnet 5 (146 pp)
Use it via API
Where to call it
- Claude API
claude-sonnet-5 - Amazon Bedrock
anthropic.claude-sonnet-5 - Google Vertex AI
claude-sonnet-5 - Microsoft Foundry / Azure
claude-sonnet-5
Supports
- Image input
- PDF input
- Structured outputs
- Reasoning control
- Tool calling
- Web search
- Prompt caching
- Batch API
Good for
- Coding, agents and everyday professional work: "near-Opus intelligence at Sonnet pricing"
- Agentic coding: SWE-bench Pro 63.2% vs 58.1% for Sonnet 4.6
- Agentic search and multimodal reasoning (BrowseComp, OSWorld-Verified)
Watch out for
Replaced by
Claude Sonnet 5.5$2.00 / $10.00
This model: $2.00 / $10.00 per 1M tokens
Compare side by sideOverview
Sonnet 5
Built to be the most agentic Sonnet model yet
- Cost
- $2.00 in
- Context
- 1M
- Input / output
- $2.00 / $10.00
- Max output
- 128K
- Knows up to
- January 2026
- Released
- 30 Jun 2026
Anthropic's latest Sonnet-class model and an upgrade to Claude Sonnet 4.6, with clear gains in coding, agentic search, multimodal reasoning and professional tasks. It is the most capable Sonnet model but does not advance Anthropic's capability frontier, and trails Opus- and Mythos-class models in almost all evaluations. p.3–4
claude-sonnet-5- Input / output per 1M
- $2.00 / $10.00
- Context window
- 1M
- Max output
- 128K
- Knows up to
- January 2026
- Reasoning
- Adaptive
- Weights
- Closed
About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses Anthropic's System Card: Claude Sonnet 5. Every claim carries its source page.