API integration

1. Available models

2. Chat and code

Copy# Non-streaming
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":"Write a Python quicksort function"}]}'

# For streaming, add "stream":true. The response uses SSE.

3. Generate an image (curl)

Copycurl -X POST "BASE/v1/images/generations" \
  -H "Authorization: Bearer $MUSE2API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A Shiba Inu wearing an astronautical helmet","size":"1:1","response_format":"url"}'

# Return
{"created":1790148495,"data":[{
  "revised_prompt":"A Shiba Inu wearing an astronautical helmet",
  "url":"http://your-server:18610/v1/media/xxxx.webp",
  "kind":"image","bytes":23860}]}

# The media URL can be rendered or downloaded directly. /v1/media/* does not require authentication.
# If you want base64, pass "response_format":"b64_json".

4. Generate video (curl, asynchronous)

Copy# ① Create task
curl -X POST "BASE/v1/videos" \
  -H "Authorization: Bearer $MUSE2API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A kitten walking on the grass","duration":5,"size":"16:9"}'
# → {"id":"task_xxx","status":"queued"}

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

5. Python (OpenAI SDK compatible)

Copyfrom openai import OpenAI
import time

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

# Generate an image
r = client.images.generate(model="muse-image", prompt="A Shiba Inu wearing an astronautical helmet")
print(r.data[0].url)

# Generate a video (asynchronous task)
import requests
t = requests.post("BASE/v1/videos", json={"prompt":"Kitten walking","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. Admin endpoints

7. Authentication

8. Connect an API client

Client compatibility