Claude Haiku 4.5
Anthropic 最快且最具成本效率的模型，適合低延遲智能應用。
上下文窗口
200k tokens
claude-haiku-4-5
最大輸出
-
1M tokens
輸入
$0.9$1
10% off1M tokens
輸出
$4.5$5
10% off1M tokens
claude-haiku-4-5試玩區
claude-haiku-4-5Click or drag
暫無輸出
定價
| 方案 | 上下文窗口 | 最大輸出 | 輸入 | 輸出 | 緩存寫入 | 緩存讀取 |
|---|---|---|---|---|---|---|
claude-haiku-4-5 | 200k tokens | - | $0.9$110% off 1M tokens | $4.5$510% off 1M tokens | $1.125$1.2510% off 1M tokens | $0.09$0.110% off 1M tokens |
1h Cache Write · $1.8 · 1M tokens
緩存讀取或緩存輸入價格適用於複用的提示詞 tokens。
README
- Anthropic 將 Haiku 4.5 定位爲其最快、最省成本的模型，同時在編程、計算機操作和智能體任務上保持接近前沿的能力。
- 它特別適合實時聊天助手、客服系統、結對編程等對延遲和成本敏感的場景。
- 官方也強調 Haiku 4.5 很適合作爲多模型工作流中的快速並行子任務執行器，與更大的模型搭配使用。
API
API
端點
POST /v1/messages認證
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
}'相關模型
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.