Capability

Video generation,available on demand.

Generate video from text with open models. Wan2.2 runs on dedicated GPUs via the OpenAI-compatible /v1/videos/generations endpoint (async: create a job, then poll), available on demand and billed per generated video.

Talk to us All models

Models you can call

Served on FlexAI today, on the OpenAI-compatible API.

Model	Context	Price	Status
Wan2.2 T2V A14B	—	$1.94 / video	Available on demand
Wan2.2 TI2V 5B	—	Custom	Available on demand
I2VGen-XL	—	Custom	Available on demand

Call it

OpenAI-compatible /v1/videos/generations, on the same key (once enabled).

# Video is async: create a job, then poll for the result.
curl https://tokens.flex.ai/v1/videos/generations \
  -H "Authorization: Bearer $FLEXAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Wan2.2-T2V-A14B-Diffusers",
    "prompt": "a serene mountain lake at dawn, gentle ripples"
  }'
# Returns a job id; poll GET https://tokens.flex.ai/v1/videos/generations/{id} until ready.

Available on demand on dedicated GPUs, through the same OpenAI-compatible key. Talk to us to enable it.

Every modality, one API key

Text, vision, image, audio, and embeddings behind one OpenAI-compatible key.

Talk to us Browse models