Claude Opus 4.6
Claude Opus，面向高难度推理、长文档和复杂工具链。
All systems normal12 providers available
Context1M
Max output128K
$2.25/ 1M tokensInput price · by access tier0.88折$0.44/ 1M tokens2折$1/ 1M tokens4.5折$2.25/ 1M tokens7折$3.5/ 1M tokens$11.25/ 1M tokensOutput price · by access tier0.88折$2.2/ 1M tokens2折$5/ 1M tokens4.5折$11.25/ 1M tokens7折$17.5/ 1M tokensCache read$0.225/1M tokens
Cache write$6.25/1M 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 |
|---|---|---|---|
| ≦200K | $2.25-$11.25/1M tokens | $0.225/1M tokens | $6.25/1M tokens |
Service performance
Success rate100%Last 24 hours
First token latency2263msLast 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-opus-4-6",
messages=[{"role": "user", "content": "用一句话介绍你自己"}],
)
print(response.choices[0].message.content)