API LongCat Distilled Text-to-Video

# 1. Start the video. It takes a minute or two.
curl https://api.uberllm.dev/v1/video/generations \
  -H "Authorization: Bearer $UBERLLM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "meituan/longcat-distilled-text-to-video", "prompt": "a red ball bouncing on green grass", "duration_seconds": 5}'

# → {"id": "<job id>", "status": "queued", "max_cost_usdc": "…", "poll_url": "/v1/video/generations/<job id>"}
#   max_cost_usdc is held while it runs (millionths of a dollar); you pay the real cost when it is done, never more than what was held.

# 2. Ask again every few seconds until "status" is "succeeded"
curl -H "Authorization: Bearer $UBERLLM_API_KEY" https://api.uberllm.dev/v1/video/generations/<job id>

# 3. Download it
curl -L -o video.mp4 -H "Authorization: Bearer $UBERLLM_API_KEY" https://api.uberllm.dev/v1/media/artifacts/<job id>/0