Claude Haiku 5.5
Claude Haiku，低延迟日常对话与分类任务。
All systems normal4 providers available
Context1M
Max output128K
$0.045/ 1M tokensInput price · by access tier0.88折$0.009/ 1M tokens2折$0.02/ 1M tokens4.5折$0.045/ 1M tokens7折$0.07/ 1M tokens$0.225/ 1M tokensOutput price · by access tier0.88折$0.044/ 1M tokens2折$0.1/ 1M tokens4.5折$0.23/ 1M tokens7折$0.35/ 1M tokensCache read$0.0045/1M tokens
Cache write$0.125/1M tokens
Capabilities
Input modality
InputText · Image
OutputText
Core capabilities
Deep thinking
Streaming
Structured output
Prompt cachingTool capabilities
Function callingAccess protocols
—
Pricing details
| Tier | Price (input–output) | Cache read | Cache write |
|---|---|---|---|
| ≦100K | $0.045-$0.225/1M tokens | $0.0045/1M tokens | $0.125/1M tokens |
| >100K | $0.225-$1.125/1M tokens | $0.0045/1M tokens | $0.125/1M tokens |
Service performance
Success rate100%Last 24 hours
First token latency1600msLast 24 hours
Quickstart
from openai import OpenAI
client = OpenAI(
base_url="https://api.apione.ai/v1",
api_key="<YOUR_API_KEY>", # 在控制台创建 API Key 后替换
)
response = client.chat.completions.create(
model="claude-haiku-5-5",
messages=[{"role": "user", "content": "用一句话介绍你自己"}],
)
print(response.choices[0].message.content)