开发者集成指南

认证与基础 URL

在仪表板生成密钥。我们的服务需要基础 URL 为 HTTPS://api.mistralapikeys.com/v1。将密钥作为 Bearer 令牌放入 Authorization 请求头中。我们支持通过 Google 或电子邮件注册，无需手机验证。

Copycurl https://api.mistralapikeys.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Convert the python loop to rust syntax"}]
  }'

Chat Completions 端点

发送 POST 请求至 /v1/chat/completions。使用模型 ID "uncensored" 进行文本生成。系统接受带有 role 和 content 字段的标准消息数组。输入 token 每 1M 个 $0.15，输出 token 每 1M 个 $0.50。

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.mistralapikeys.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

流式响应与 Token 计数

通过在请求中将 stream 设置为 true 来启用流式传输。API 返回包含部分数据块的服务器发送的事件。最后一个数据块包含完整的令牌使用统计信息，以便准确计费。此方法降低了长输出的感知延迟。

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.mistralapikeys.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

流式传输

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)