Scan to join WeChat groupClaude Sonnet 5
Claude Sonnet 5 for coding, agents and professional work at scale
Claude Sonnet 5 is an Anthropic Claude model for coding, agents and professional work at scale, with a focus on long-context understanding, writing quality and reliable analysis.
starsCapabilities
visibilityVision understandingcodeFunction callingstreamStreaming outputdata_objectStructured output
paymentsContext and pricing
Context limit1,000,000
Max output128,000
Knowledge cutoff2026-01-31
Input price$2/ 1M tokens
Output price$10/ 1M tokens
Cached input price$0.2/ 1M tokens
descriptionOverview
Overview
Claude Sonnet 5 is part of the official Anthropic Claude model family, with model ID claude-sonnet-5. Claude models are commonly evaluated for long-context understanding, careful writing, coding assistance and safety-aware enterprise workflows.
Best for
Use Claude Sonnet 5 when your product needs document analysis, code review, enterprise Q&A, agent workflows or high-quality writing. Test long-context reliability, refusal boundaries, tool behavior, cost and latency before production.
lightbulbUse cases
- Long-document analysis and summarization
- Code review and rewriting
- Enterprise knowledge Q&A
- Agent and tool workflows
thumb_upStrengths
- Strong fit for long-context tasks
- Careful writing and analysis style
- Useful for enterprise safety requirements
- Easy to tier against Haiku, Sonnet and Opus
infoLimitations
- Cost and latency vary by tier
- Tool workflows and long-running tasks need testing
- Some workloads may be better on a smaller model
- Capabilities depend on Anthropic documentation