Gemini Video Vision API: AI Text Generation

Gemini Video Vision API Reference

Endpoint

POST https://api.muapi.ai/api/v1/gemini-video-vision

Submit a job with your MuApi API key in the x-api-key header, then poll https://api.muapi.ai/api/v1/predictions/{request_id}/result until status is completed.

Parameters

Name	Type	Required	Description
model	string	No	Gemini model to use for video understanding. gemini-2.5-pro was removed from this enum after Google deprecated it for new users (returns a 404 NOT_FOUND); gemini-2.5-flash is the only currently supported option.Options: gemini-2.5-flashDefault: "gemini-2.5-flash"
prompt	string	Yes	The question or instruction describing what to analyze in the video.
video_url	string	Yes	URL of the video to analyze.
system_prompt	string	No	Optional system-level instruction to guide the model's analysis style.

cURL example

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/gemini-video-vision \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"<prompt>","video_url":"https://example.com/your-video_url"}' | jq -r .request_id)

curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY"

Python example

import os, time, requests

API = "https://api.muapi.ai/api/v1"
headers = {"x-api-key": os.environ["MUAPI_API_KEY"]}

r = requests.post(f"{API}/gemini-video-vision", headers=headers, json={"prompt":"<prompt>","video_url":"https://example.com/your-video_url"})
request_id = r.json()["request_id"]

while True:
    res = requests.get(f"{API}/predictions/{request_id}/result", headers=headers).json()
    if res["status"] == "completed":
        print(res["outputs"]); break
    if res["status"] == "failed":
        raise RuntimeError(res.get("error"))
    time.sleep(3)

Full docs and agent/MCP integration: llms.txt. Get an API key at muapi.ai/access-keys.