Quickstart

5 行代码接入

Solquir API 完全兼容 OpenAI Chat Completions 协议。已经在用 OpenAI SDK？只需改 base URL 和 API key。

前提

一个 Solquir 账号（在 /signup 创建）
一个 API key（在 /dashboard/keys 生成；以 solqc_ 开头）
把 key 写进环境变量 SOLQUIR_API_KEY

语言示例

选你的语言，复制粘贴跑：

cURL

bash

curl https://solquir.io/api/v1/chat/completions \
  -H "Authorization: Bearer $SOLQUIR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "solquir-v1",
    "messages": [
      {"role": "user", "content": "Hello, Solquir!"}
    ]
  }'

Node · TypeScript

装包：npm install openai

typescript

import OpenAI from "openai"

const client = new OpenAI({
  apiKey: process.env.SOLQUIR_API_KEY,
  baseURL: "https://solquir.io/api/v1",
})

const res = await client.chat.completions.create({
  model: "solquir-v1",
  messages: [{ role: "user", content: "Hello, Solquir!" }],
})

console.log(res.choices[0].message.content)

Python

装包：pip install openai

python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["SOLQUIR_API_KEY"],
    base_url="https://solquir.io/api/v1",
)

res = client.chat.completions.create(
    model="solquir-v1",
    messages=[{"role": "user", "content": "Hello, Solquir!"}],
)

print(res.choices[0].message.content)

Go

装包：go get github.com/sashabaranov/go-openai

go

package main

import (
    "context"
    "fmt"
    "os"

    openai "github.com/sashabaranov/go-openai"
)

func main() {
    cfg := openai.DefaultConfig(os.Getenv("SOLQUIR_API_KEY"))
    cfg.BaseURL = "https://solquir.io/api/v1"
    client := openai.NewClientWithConfig(cfg)

    res, _ := client.CreateChatCompletion(context.Background(),
        openai.ChatCompletionRequest{
            Model: "solquir-v1",
            Messages: []openai.ChatCompletionMessage{
                {Role: "user", Content: "Hello, Solquir!"},
            },
        })
    fmt.Println(res.Choices[0].Message.Content)
}

流式响应

Solquir 支持 OpenAI 兼容的 SSE 流式响应。把 stream: true加到请求里就行。

node · streaming

const stream = await client.chat.completions.create({
  model: "solquir-v1",
  messages: [{ role: "user", content: "写一首唐诗" }],
  stream: true,
})

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "")
}

下一步

模型列表 — 看哪个 model slug 适合你的任务
Endpoint 详细 — 全部参数和返回值
错误码 — 4xx/5xx 处理建议

TIP所有调用都附带 thinking 字段，包含路由决策、工具调用、 token 用量。`X-Solquir-Trace-Id` header 用于排障联系 support 时附带。