anthropic logo
anthropic

Anthropic: Claude Sonnet 4.5 (batch)

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. $1.50 per million input tokens, $7.50 per million output tokens. 1,000,000 token context window, maximum output of 64,000 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.

模型概览

模型规格

上下文
1,000,000 tokens
最大输出
64,000 tokens
架构
text+image+file->text
分词器
Claude
知识截止时间
2025-01-31
内容审核
OPENROUTER

完整价格

同步自 OpenRouter。Token 价格均按每百万 Token 展示。

输入
$1.5
/M tokens
  • ≤200K$1.5
  • >200K$3
输出
$7.5
/M tokens
  • ≤200K$7.5
  • >200K$11.25
缓存读取
$0.15
/M tokens
  • ≤200K$0.15
  • >200K$0.3
缓存写入
$1.875
/M tokens
  • ≤200K$1.875
  • >200K$3.75
Cache Write (1h)
$3
/M tokens
  • ≤200K$3
  • >200K$6
网页搜索
$10
/1K calls
API

模型配置

默认参数

temperature
1
top_p
1

推理能力

内容审核
默认参数
API

快速调用

通过 OpenRouter 的 OpenAI 兼容 API 调用这个确切的模型 ID。

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-sonnet-4.5:batch","messages":[{"role":"user","content":"Hello!"}]}'
能力与模态

输入输出

输入
textimagefile
输出
text
推理能力

API

支持的 API 参数

include_reasoningmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
可用提供方

7 个提供方

在 OpenRouter 查看实时 Provider

Provider 可用性、延迟、吞吐量和路由会持续变化,请前往来源页面查看实时运行数据。

OpenRouter

Google

unknown
上下文
1M
最大输出
64K
输入
$3.00
输出
$15.00
缓存读取
$0.300
缓存写入
$3.75

Azure

unknown
上下文
200K
最大输出
64K
输入
$3.00
输出
$15.00
缓存读取
$0.300
缓存写入
$3.75

Claude Platform on AWS

unknown
上下文
1M
最大输出
64K
输入
$3.00
输出
$15.00
缓存读取
$0.300
缓存写入
$3.75

Amazon Bedrock

unknown
上下文
1M
最大输出
64K
输入
$3.00
输出
$15.00
缓存读取
$0.300
缓存写入
$3.75

Anthropic

unknown
上下文
1M
最大输出
64K
输入
$3.00
输出
$15.00
缓存读取
$0.300
缓存写入
$3.75

Amazon Bedrock

unknown
上下文
1M
最大输出
64K
输入
$3.30
输出
$16.50
缓存读取
$0.330
缓存写入
$4.13

Google

unknown
上下文
1M
最大输出
64K
输入
$3.30
输出
$16.50
缓存读取
$0.330
缓存写入
$4.13
anthropic

个模型

全部模型
anthropic logoanthropic

Claude Opus 5 (Fast)

Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

上下文
1M
输入
text · image · file
输出
text
输入: $10.00输出: $50.00每百万 Token
查看模型详情
anthropic logoanthropic

Claude Opus 5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

上下文
1M
输入
text · image · file
输出
text
输入: $5.00输出: $25.00每百万 Token
查看模型详情
anthropic logoanthropic

Claude Opus 5 (batch)

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

上下文
1M
输入
text · image · file
输出
text
输入: $2.50输出: $12.50每百万 Token
查看模型详情
anthropic logoanthropic

Anthropic: Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

上下文
1M
输入
text · image · file
输出
text
输入: $2.00输出: $10.00每百万 Token
查看模型详情