Vidu Q3 Text to Video API

fal-ai/vidu/q3/text-to-videoVideo

Make videos with Vidu Q3 Text to Video through UberLLM: $0.0595 / job. Requests are served by third-party providers. Made by vidu. UberLLM adds no fee to these prices.

Vidu Q3 Text to Video pricing

Price now
$0.0595 / job
Official price
$0.0595 / job

Each request is sent to an available third-party provider for this model and retried if the provider fails before it starts answering. UberLLM adds no fee to these prices.

How to use it

Start the job, check on it, then download the video. You only pay when it is made.

bash
# 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": "fal-ai/vidu/q3/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 above the listed price.

# 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

The clip lengths, sizes and other choices this model takes: GET https://api.uberllm.dev/v1/models/fal-ai/vidu/q3/text-to-video. Add "validate": true to see the most a request can cost without paying. Guide

Vidu Q3 Text to Video API FAQ

How much does Vidu Q3 Text to Video cost?

Vidu Q3 Text to Video is $0.0595 / job through UberLLM right now. That price for a video has no UberLLM fee on top. A job that fails costs nothing.

How do I make a video with Vidu Q3 Text to Video?

Send a POST to https://api.uberllm.dev/v1/video/generations with your UberLLM key, model "fal-ai/vidu/q3/text-to-video" and a prompt. You get a job id back; ask https://api.uberllm.dev/v1/video/generations/<job id> until it says "succeeded", then download it from https://api.uberllm.dev/v1/media/artifacts/<job id>/0.

More vidu models