文档 / 大模型 / 对话
大模型 / 对话
RelayRouter 通过完全兼容 OpenAI 的 API 提供对话模型。如果你已经在使用 OpenAI SDK,只需修改 base URL 和 API 密钥,无需更改其他代码。
#Base URL
https://relayrouter.io/v1#模型示例
| 模型 ID | 服务商 |
|---|---|
| claude-opus-4-8 | Anthropic |
| gpt-5-5 | OpenAI |
| deepseek-v4-flash | DeepSeek |
完整模型目录可在模型页面浏览,或通过 GET /v1/models 获取。
#Python
main.pypython
from openai import OpenAI
import os
client = OpenAI(
api_key=os.environ["RELAYROUTER_API_KEY"],
base_url="https://relayrouter.io/v1",
)
response = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain quantum computing in simple terms."},
],
temperature=0.7,
max_tokens=1024,
)
print(response.choices[0].message.content)#Python:流式输出
stream.pypython
stream = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Write a short story about a robot."}],
stream=True,
)
for chunk in stream:
content = chunk.choices[0].delta.content
if content:
print(content, end="", flush=True)#Node.js / TypeScript
index.tstypescript
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.RELAYROUTER_API_KEY,
baseURL: "https://relayrouter.io/v1",
});
const response = await client.chat.completions.create({
model: "deepseek-v4-flash",
messages: [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing in simple terms." },
],
});
console.log(response.choices[0].message.content);#cURL
terminalbash
curl https://relayrouter.io/v1/chat/completions \
-H "Authorization: Bearer $RELAYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain quantum computing in simple terms."}
],
"temperature": 0.7,
"max_tokens": 1024
}'#常用参数
| 参数 | 类型 | 说明 |
|---|---|---|
model | string | 你的密钥模型列表中的模型 ID |
messages | array | 对话消息,包含角色(system | user | assistant)和内容 |
temperature | number | 采样温度,取值 0 到 2。值越高输出越随机 |
max_tokens | integer | 生成的最大 token 数 |
stream | boolean | 若为 true,token 将以 SSE 数据块的形式发送 |
top_p | number | 核采样,可作为 temperature 的替代 |
stop | string | array | 最多 4 个停止序列 |
tools | array | 模型可调用的工具(OpenAI tool-use schema) |
不同模型支持的参数有所不同;上游会忽略不支持的参数。请求与响应的结构请参阅 Chat Completions 参考。