Claude Haiku 4.5

Claude Haiku 4.5 参考:生命周期状态、各平台上的模型 ID、上下文窗口、输出限制、定价和迁移资源。Claude Haiku 4.5 是旧版模型;Claude Haiku 5.5 是当前的 Haiku 模型。

Legacy. Released October 15, 2025.

Although Claude Haiku 4.5 is still available, you should consider migrating to Claude Haiku 5.5. See Claude Haiku 5.5 · Migrate to Claude Haiku 5.5

Model ID: claude-haiku-4-5-20251001

Context window: 200K tokens · Max output: 64K tokens · Input pricing: $1 / MTok · Output pricing: $5 / MTok

Announcement

与当前模型阵容的比较

ModelContextMax outputPrice / MTokThinkingDefault effortKnowledge cutoff
Claude Fable 5.21M128K$8 / $40Adaptive (always on)highJun 2026
Claude Opus 5.51M128K$4 / $20Adaptive (always on)mediumJun 2026
Claude Sonnet 5.51M128K$2 / $10AdaptivehighJun 2026
Claude Haiku 5.51M128KFrom $0.10 / $0.50AdaptivemediumJun 2026
Claude Haiku 4.5 (this model)200K64K$1 / $5Extended—Feb 2025
  • 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.
  • 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-haiku-4-5-20251001
Claude API aliasclaude-haiku-4-5
Amazon Bedrockanthropic.claude-haiku-4-5
Amazon Bedrock (bedrock-runtime)global.anthropic.claude-haiku-4-5-20251001-v1:0
Claude Models on Google Cloud (Google managed)claude-haiku-4-5@20251001
Microsoft Foundryclaude-haiku-4-5
Claude Platform on AWSclaude-haiku-4-5
Claude Models on Google Cloud (Anthropic managed)claude-haiku-4-5-20251001

Pricing

FeatureValue
Input$1 / MTok
Output$5 / MTok
5m cache write$1.25 / MTok
1h cache write$2 / MTok
Cache read$0.10 / MTok
Batch API50% discount on input and output

Full price list

Capabilities

FeatureValue
Context window200K tokens
Max output64K tokens
ThinkingExtended
Default effortNot supported
Input → outputText and images → text
Reliable knowledge cutoffFeb 2025
Training data cutoffJul 2025

Availability

FeatureValue
StatusActive (legacy)
ReleasedOctober 15, 2025
RetirementNot sooner than October 15, 2026
PlatformsClaude API, Amazon Bedrock, Amazon Bedrock (bedrock-runtime), Claude Models on Google Cloud (Google managed), Microsoft Foundry, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed)

须知事项

  • claude-haiku-4-5 是一个便捷别名,会解析为固定快照 claude-haiku-4-5-20251001。请参阅模型 ID 与版本管理。
  • Claude Haiku 4.5 使用手动 “extended thinking”(扩展思考)(thinking.type: "enabled"),而非自适应思考。
  • 可通过 Models API 以编程方式查询限制和功能。

资源

扩展思考

Claude Haiku 4.5 支持使用 budget_tokens 的手动扩展思考。

参考

系统提示

Claude Haiku 4.5 在 claude.ai 和 Claude 应用中使用的系统提示。

系统卡

Claude Haiku 4.5 的安全评估和部署决策。

定价

完整价格表,包括批量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