Claude Opus 5.5

Claude Opus 5.5 概述:其用途、各平台上的模型 ID、上下文窗口、输出限制、定价、可用性,以及使用它进行构建的指南和资源。

Latest. Released September 22, 2026.

For long-running agentic coding and knowledge work

Model ID: claude-opus-5-5

Context window: 1M tokens · Max output: 128K tokens · Input pricing: $4 / MTok · Output pricing: $20 / MTok

Announcement · What’s new · Migration guide

概述

Claude Opus 5.5 专为长时间运行的智能体编码和知识工作而构建。典型用途包括持续数小时的自主编码智能体、大规模重构、复杂系统工程、视觉密集型工作流和计算机使用。

对比情况

ModelContextMax outputPrice / MTokLatencyThinkingDefault effortKnowledge cutoff
Claude Fable 5.21M128K$8 / $40ModerateAdaptive (always on)highJun 2026
Claude Opus 5.5 (this model)1M128K$4 / $20ModerateAdaptive (always on)mediumJun 2026
Claude Sonnet 5.51M128K$2 / $10FastAdaptivehighJun 2026
Claude Haiku 5.51M128KFrom $0.10 / $0.50FastestAdaptivemediumJun 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 5.2, Claude Mythos 5.2, 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.
  • Latency: Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
  • 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

PlatformModel ID
Claude APIclaude-opus-5-5
Amazon Bedrockanthropic.claude-opus-5-5
Claude Models on Google Cloud (Google managed)claude-opus-5-5
Microsoft Foundryclaude-opus-5-5
Claude Platform on AWSclaude-opus-5-5
Claude Models on Google Cloud (Anthropic managed)claude-opus-5-5

Pricing

FeatureValue
Input$4 / MTok
Output$20 / MTok
5m cache write$5 / MTok
1h cache write$8 / MTok
Cache read$0.20 / MTok
Batch API50% discount on input and output

Full price list

Capabilities

FeatureValue
Context window1M tokens
Max output128K tokens
Max output (Batch API, beta)300K tokens
ThinkingAdaptive (always on)
Default effortmedium
Comparative latencyModerate
Input → outputText and images → text
Reliable knowledge cutoffJun 2026
Training data cutoffJun 2026

Availability

FeatureValue
StatusActive (latest)
ReleasedSeptember 22, 2026
RetirementNot sooner than September 22, 2027
PlatformsClaude API, Amazon Bedrock, Claude Models on Google Cloud (Google managed), Microsoft Foundry, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed)

须知事项

  • “Adaptive thinking”(自适应思考)始终开启,且无法关闭。您可以使用 effort 参数控制思考深度。
  • 在 Message Batches API 上,使用 output-300k-2026-03-24 beta 标头时,Claude Opus 5.5 最多支持 300k 个输出令牌。
  • 最小可缓存提示长度为 512 个令牌。请参阅提示缓存。
  • 使用 Models API 以编程方式查询限制和功能。

资源

Effort

用于控制思考深度、延迟和成本。为每种工作负载选择合适的级别。

自适应思考

自适应思考的工作原理以及思考块的保留方式。

快速模式

Claude API 上更低延迟的 Claude Opus 5.5,单独定价。

参考

系统提示

Claude Opus 5.5 在 claude.ai 和 Claude 应用中使用的系统提示。

系统卡

Claude Opus 5.5 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。

模型弃用

每个 Claude 模型的生命周期状态和退役承诺。

文档内容持续同步更新