Background texture
ModelMax

快速上手

5 分钟内开始使用 ModelMax。你将发送你的第一个对话补全请求并使用流式响应。

1. 获取 API 密钥

使用 Google 账号登录 ModelMax 控制台，然后在 设置 → API 密钥 中创建一个 API 密钥。

2. 发送对话补全请求

curl -X POST https://api.modelmax.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MODELMAX_API_KEY" \
  -d '{
    "model": "gemini-3-flash-preview",
    "messages": [
      { "role": "user", "content": "用一句话解释量子计算。" }
    ]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.modelmax.io/v1",
)

response = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[
        {"role": "user", "content": "用一句话解释量子计算。"}
    ],
)

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

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your-api-key",
  baseURL: "https://api.modelmax.io/v1",
});

const response = await client.chat.completions.create({
  model: "gemini-3-flash-preview",
  messages: [
    { role: "user", content: "用一句话解释量子计算。" },
  ],
});

console.log(response.choices[0].message.content);

3. 流式响应

添加 "stream": true 以通过 Server-Sent Events 逐步接收生成的 token。

curl -X POST https://api.modelmax.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MODELMAX_API_KEY" \
  -d '{
    "model": "gemini-3-flash-preview",
    "messages": [
      { "role": "user", "content": "写一首关于 API 的俳句。" }
    ],
    "stream": true
  }'

stream = client.chat.completions.create(
    model="gemini-3-flash-preview",
    messages=[{"role": "user", "content": "写一首关于 API 的俳句。"}],
    stream=True,
)

for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

const stream = await client.chat.completions.create({
  model: "gemini-3-flash-preview",
  messages: [{ role: "user", content: "写一首关于 API 的俳句。" }],
  stream: true,
});

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

4. 生成视频

视频生成使用异步队列 API。提交任务，轮询状态，然后下载结果。

# 提交
curl -X POST https://api.modelmax.io/v1/queue/veo-3 \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MODELMAX_API_KEY" \
  -d '{ "prompt": "A cat riding a skateboard through a neon-lit city" }'

# 响应 → { "request_id": "...", "status_url": "...", "response_url": "..." }

# 轮询状态
curl https://api.modelmax.io/v1/queue/veo-3/requests/{request_id}/status \
  -H "Authorization: Bearer $MODELMAX_API_KEY"

# 当状态为 COMPLETED 时，获取结果
curl https://api.modelmax.io/v1/queue/veo-3/requests/{request_id} \
  -H "Authorization: Bearer $MODELMAX_API_KEY"

查看完整的视频生成指南了解完整工作流。

下一步