Claude Sonnet 4.6
Anthropic 面向日常生产使用的高性能模型，适合编程、智能体和专业工作流。
上下文窗口
1M tokens
claude-sonnet-4-6
最大输出
-
1M tokens
输入
$2.7$3
10% off1M tokens
输出
$13.5$15
10% off1M tokens
claude-sonnet-4-6试玩区
claude-sonnet-4-6Click or drag
暂无输出
定价
| 方案 | 上下文窗口 | 最大输出 | 输入 | 输出 | 缓存写入 | 缓存读取 |
|---|---|---|---|---|---|---|
claude-sonnet-4-6 | 1M tokens | - | $2.7$310% off 1M tokens | $13.5$1510% off 1M tokens | $3.375$3.7510% off 1M tokens | $0.27$0.310% off 1M tokens |
1h Cache Write · $5.4 · 1M tokens
缓存读取或缓存输入价格适用于复用的提示词 tokens。
README
- Anthropic 将 Sonnet 4.6 定位为适合日常使用和规模化生产部署的前沿模型，覆盖编程、智能体和专业知识工作。
- 它既支持快速响应，也支持扩展式逐步思考，在指令跟随、工具使用和长时任务自治方面表现突出。
- 官方资料强调 Sonnet 4.6 在很多工作负载上能提供接近 Opus 的表现，但成本和效率更优。
API
API
端点
POST /v1/messages认证
Authorization: Bearer YOUR_REACH_API_KEY anthropic-version: 2023-06-01 Content-Type: application/json
示例
curl -X POST "https://direct.reachapi.ai/v1/messages" \
-H "Authorization: Bearer YOUR_REACH_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "YOUR_MODEL_ID",
"messages": [
{
"role": "user",
"content": "Introduce ReachAPI in one sentence."
}
],
"max_tokens": 512,
"temperature": 0.2
}'相关模型
Claude Fable 5
Anthropic's most capable widely released model for next-generation intelligence and long-running agents.
Claude Opus 5
Anthropic's flagship model for deep reasoning, complex agentic coding, and long-horizon enterprise work.
Claude Sonnet 5
Anthropic's new Sonnet model for extended-context coding, agents, and enterprise production workflows.
Claude Opus 4.8
Anthropic's newest Opus-tier model for complex reasoning, long-horizon agentic coding, and high-autonomy enterprise work.
Claude Opus 4.7
Anthropic's premium Opus model for advanced coding, vision-heavy review, and long-running enterprise agents.
Claude Opus 4.6
Anthropic's most capable model for coding, agents, and high-stakes enterprise work.