Claude Sonnet 5.5
Anthropic 生产级 Sonnet 模型,面向编程、智能体和长上下文企业工作负载。
上下文窗口
1M tokens
claude-sonnet-5-5
最大输出
-
1M tokens
输入
$1.8$2.00
10% off1M tokens
输出
$9$10.00
10% off1M tokens
claude-sonnet-5-5试玩区
claude-sonnet-5-5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-5-5 | 1M tokens | - | $1.8$2.0010% off 1M tokens | $9$10.0010% off 1M tokens | $2.25$2.5010% off 1M tokens | $0.18$0.2010% off 1M tokens |
Anthropic 官方刊例价,所有价格均为每 100 万 tokens。
提示缓存读取按输入单价的 10% 计费,缓存写入按输入单价的 1.25 倍计费。
缓存读取或缓存输入价格适用于复用的提示词 tokens。
README
- Claude Sonnet 5.5 延续 Sonnet 系列的生产标准:100 万 tokens 上下文窗口、强大的编程与长上下文推理,以及永久 $2/$10 价格。
- 提示缓存读取为输入单价的 10%(最高节省 90%),缓存写入为输入单价的 1.25 倍,Batch API 对符合条件的负载提供 5 折优惠。
- ReachAPI 通过 `claude-sonnet-5-5` 模型代码,在 Claude Messages 协议上开放该模型。
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 Haiku 5.5
Anthropic's fastest, most cost-efficient model for low-latency assistants and high-volume automation.
Claude Opus 5.5
Anthropic's flagship model for deep reasoning, complex agentic coding, and long-horizon enterprise work.
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.
