Legacy. Released June 30, 2026.

Although Claude Sonnet 5 is still available, you should consider migrating to Claude Sonnet 5.5. See Claude Sonnet 5.5 · Migrate to Claude Sonnet 5.5

Model ID: claude-sonnet-5

Context window: 1M tokens · Max output: 128K tokens · Input pricing: $2 / MTok · Output pricing: $10 / MTok

Announcement

与当前模型阵容的比较

Model Context Max output Price / MTok Thinking Default effort Knowledge cutoff
Claude Fable 5.1 1M 128K $10 / $50 Adaptive (always on) high Jun 2026
Claude Opus 5.5 1M 128K $4 / $20 Adaptive (always on) medium Jun 2026
Claude Sonnet 5.5 1M 128K $2 / $10 Adaptive high Jun 2026
Claude Sonnet 5 (this model) 1M 128K $2 / $10 Adaptive high Jan 2026
Claude Haiku 5.5 1M 128K From $0.10 / $0.50 Adaptive medium Jun 2026
  • Context: 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
  • Max output: Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
  • Price / MTok: Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
  • Thinking: Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget_tokens mode on earlier models.
  • Default effort: The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
  • Knowledge cutoff: Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.

规格

Model IDs

Platform Model ID
Claude API claude-sonnet-5
Amazon Bedrock anthropic.claude-sonnet-5
Claude Models on Google Cloud (Google managed) claude-sonnet-5
Microsoft Foundry claude-sonnet-5
Claude Platform on AWS claude-sonnet-5
Claude Models on Google Cloud (Anthropic managed) claude-sonnet-5

Pricing

Feature Value
Input $2 / MTok
Output $10 / MTok
5m cache write $2.50 / MTok
1h cache write $4 / MTok
Cache read $0.20 / MTok
Batch API 50% discount on input and output

Full price list

Capabilities

Feature Value
Context window 1M tokens
Max output 128K tokens
Max output (Batch API, beta) 300K tokens
Thinking Adaptive
Default effort high
Input → output Text and images → text
Reliable knowledge cutoff Jan 2026
Training data cutoff Jan 2026

Availability

Feature Value
Status Active (legacy)
Released June 30, 2026
Retirement Not sooner than June 30, 2027
Platforms Claude API, Amazon Bedrock, Claude Models on Google Cloud (Google managed), Microsoft Foundry, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed)

须知

  • 在 Message Batches API 上，Claude Sonnet 5 通过 output-300k-2026-03-24 “beta header”（测试版标头）支持最多 300k “output tokens”（输出令牌）。
  • 设置 temperature、top_p 或 top_k 会返回 400 错误。
  • 使用 Models API 以编程方式查询限制和功能。

资源

  • 迁移到 Claude Sonnet 5.5：从 Claude Sonnet 5 迁移到 Claude Sonnet 5.5 时会发生哪些变化。

  • Claude Sonnet 5.5：当前的 Sonnet 模型：概述、规格和资源。

  • Claude Sonnet 5 提示指南：针对特定模型的提示指导。

  • 自适应思考：在 Claude Sonnet 5 上默认开启。使用 effort 控制思考深度。

  • Effort：在 Claude API 和 Claude Code 上，effort 默认为 high。请根据每个工作负载选择级别。

  • 上下文窗口：默认 1M 令牌。了解上下文窗口的计算和管理方式。

参考

  • 系统提示：Claude Sonnet 5 在 claude.ai 和 Claude 应用中使用的系统提示。

  • 系统卡：Claude Sonnet 5 的安全评估和部署决策。

  • 定价：完整价目表，包括批处理折扣和提示缓存费率。

  • 模型 ID 和版本控制：模型 ID、别名和固定快照的工作方式。

  • 模型弃用：每个 Claude 模型的生命周期状态和停用承诺。