连接指南

1. 可用模型

2. 聊天 / 编程

复制# 非流式
curl -X POST "BASE/v1/chat/completions" \
  -H "Authorization: Bearer $MUSE2API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"muse-spark","messages":[{"role":"user","content":"用 Python 写一个快速排序算法"}]}'

# 流式：在其后加 "stream":true 以接收标准 SSE

3. 生成图片（curl）

复制curl -X POST "BASE/v1/images/generations" \
  -H "Authorization: Bearer $MUSE2API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"一只柴犬戴着宇航员头盔","size":"1:1","response_format":"url"}'

# 结果
{"created":1790148495,"data":[{
  "revised_prompt":"一只柴犬戴着宇航员头盔",
  "url":"http://your-server:18610/v1/media/xxxx.webp",
  "kind":"image","bytes":23860}]}

# url 是用于显示/下载的完整地址；/v1/media/* 无需鉴权。
# 要接收 base64，设置 "response_format":"b64_json".

4. 生成视频（curl，后台运行）

复制# ① 创建任务
curl -X POST "BASE/v1/videos" \
  -H "Authorization: Bearer $MUSE2API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"一只猫在草地上走","duration":5,"size":"16:9"}'
# → {"id":"task_xxx","status":"queued"}

# ② 查看结果
curl "BASE/v1/videos/task_xxx" -H "Authorization: Bearer $MUSE2API_KEY"
# → {"status":"succeeded","result":{"url":"/v1/media/xxx.mp4"}}

5. Python（兼容 OpenAI SDK）

复制from openai import OpenAI
import time

client = OpenAI(base_url="BASE/v1", api_key="m2a_...")

# 生成图片
r = client.images.generate(model="muse-image", prompt="一只柴犬戴着宇航员头盔")
print(r.data[0].url)

# 生成视频（任务在后台运行，使用专用 API）
  import requests
t = requests.post("BASE/v1/videos", json={"prompt":"猫在走路","duration":5},
                  headers={"Authorization":"Bearer m2a_..."}).json()
while True:
    s = requests.get(f"BASE/v1/videos/{t['id']}",
                     headers={"Authorization":"Bearer m2a_..."}).json()
    if s["status"] in ("succeeded","failed"): break
    time.sleep(5)
print(s)

6. 管理 API

7. 鉴权

8. 连接应用和 agent

兼容性