Claude Sonnet 5Latest

The best combination of speed and intelligence

Context window: 1Mtokens
Max output: 128Ktokens
Input pricing: $2/ MTok
Output pricing: $10/ MTok

概述

Claude Sonnet 5 是 Anthropic Sonnet 模型系列的下一代产品。它是 Claude Sonnet 4.6 的直接替换升级，包含三项行为变更：adaptive thinking（自适应思考）默认开启；手动 extended thinking（扩展思考）现在会返回 400 错误（它在 Claude Sonnet 4.6 上已被弃用）；将采样参数（temperature、top_p、top_k）设置为非默认值会返回 400 错误。本页总结了发布时的所有新内容，包括新的 tokenizer（分词器）。

Claude Sonnet 5 的新功能

对比情况

Model	Context	Max output	Price / MTok	Latency	Thinking	Default effort	Knowledge cutoff
Claude Fable 5.1	1M	128K	$10 / $50	Slower	Adaptive (always on)	`high`	Jun 2026
Claude Opus 5	1M	128K	$5 / $25	Moderate	Adaptive	`high`	May 2026
Claude Sonnet 5This model	1M	128K	$2 / $10	Fast	Adaptive	`high`	Jan 2026
Claude Haiku 4.5	200K	64K	$1 / $5	Fastest	Extended	—	Feb 2025

规格

Model IDs

Claude API
Amazon Bedrock
Google Cloud
Microsoft Foundry
Claude Platform on AWS

Pricing

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: Pricing

Capabilities

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

Availability

Status: Active (latest)
Released: June 30, 2026
Retirement: Not sooner than June 30, 2027
Platforms: Claude APIAmazon Bedrock Google Cloud Microsoft Foundry Claude Platform on AWS

须知事项

在 Message Batches API 上，Claude Sonnet 5 通过 output-300k-2026-03-24 beta 请求头支持最多 300k 输出令牌。
将 temperature、top_p 或 top_k 设置为非默认值会返回 400 错误。请参阅 Claude Sonnet 5 的新特性。
使用 Models API 以编程方式查询限制和功能。