Claude Opus 4.8
Anthropic 最新 Opus 档位模型，适合复杂推理、长周期智能体编程和高自治企业工作。
上下文窗口
200k tokens
claude-opus-4-8
最大输出
-
1M tokens
输入
$4.5$5
10% off1M tokens
输出
$22.5$25
10% off1M tokens
claude-opus-4-8试玩区
claude-opus-4-8Click 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-opus-4-8 | 200k tokens | - | $4.5$510% off 1M tokens | $22.5$2510% off 1M tokens | $5.625$6.2510% off 1M tokens | $0.45$0.510% off 1M tokens |
1h Cache Write · $9 · 1M tokens
缓存读取或缓存输入价格适用于复用的提示词 tokens。
README
- Claude Opus 4.8 面向高自治工作：长周期编程智能体、复杂重构、多步骤调试，以及需要模型在长会话中规划、校验并持续保留上下文的企业任务。
- Anthropic 强调其自适应思考能力，可在速度和深度之间取得平衡，让团队在关键步骤使用更深推理，同时让常规任务保持响应效率。
- 该模型还引入 Fast Mode research preview，并将可缓存 prompt 的最低长度降至 1,024 tokens，便于缓存可复用系统提示词和工具密集型智能体上下文。
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 4.7
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.
Claude Sonnet 4.6
Anthropic's high-performance daily driver for coding, agents, and professional workflows at scale.