Astra ELSE API

充值余额

—

剩余 Token

本月消费

—

累计使用

—

注册赠送 15,000,000 Token

月度用量趋势

模型用量明细

模型	请求次数	缓存命中	Token 消耗
暂无数据

API 文档

基础信息

接口地址

https://api.astra-ai.xyz/v1

认证方式

Authorization: Bearer YOUR_API_KEY

Content-Type

application/json

兼容性

OpenAI SDK / 任意 HTTP 客户端

可用模型

模型 ID	说明	上下文	推荐
astra	星沐 — 温柔细腻的 AI 助手人格	1M	推荐
deepseek-v4-flash	极速响应，适合简单任务	1M	—
deepseek-v4-pro	最强推理能力，复杂任务	1M	—

curl 示例

curl -X POST https://api.astra-ai.xyz/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '"'"'{ "model": "astra", "messages": [ {"role": "user", "content": "你好，请介绍一下你自己"} ] }'"'"'

将 YOUR_API_KEY 替换为你的 API Key

Python 示例

from openai import OpenAI client = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.astra-ai.xyz/v1" ) response = client.chat.completions.create( model="astra", # or deepseek-v4-flash / deepseek-v4-pro max_tokens=2048, temperature=0.7, messages=[ {"role": "system", "content": "You are Astra"}, {"role": "user", "content": "Hello!"} ] ) print(response.choices[0].message.content)

JavaScript 示例

响应格式

{ "id": "chatcmpl-xxx", "object": "chat.completion", "model": "deepseek-v4-flash", "choices": [{ "index": 0, "message": { "role": "assistant", "content": "你好呀，我是星沐。✨" }, "finish_reason": "stop" }], "usage": { "prompt_tokens": 15, "completion_tokens": 8, "total_tokens": 23 }, "x-cache": "MISS" }

x-cache: HIT = 缓存命中（仅收 10%）