Videos

Use it when

• Your upstream provider exposes an OpenAI-style video endpoint.
• You want to generate videos from a text prompt with the same Prismatic API key as text and image endpoints.
• The selected model and provider route both support videos.

Code examples

curl https://api.prismaticapi.com/v1/videos   -H "Authorization: Bearer $PRISMATIC_API_KEY"   -H "Content-Type: application/json"   -d '{
    "model": "veo-3-1",
    "prompt": "A serene koi pond at sunset, cinematic",
    "size": "1080x1920",
    "duration": 8,
    "n": 1
  }'

Parameters

• model (string, required) — Public model ID returned by GET /v1/models.
• prompt (string, required) — Text prompt describing the video to generate.
• size, duration, n and other provider-supported fields are forwarded to the upstream video endpoint.

Billing and limits

• API-key and account rate limits are checked before generation.
• Subscription quota is reserved before generation and settled afterward.
• PAYG video cost is retail_generation_usd * n for this phase, not per second and not token-usage based.
• If the model or provider route does not support videos, the request fails before upstream calls.

Notes

• The endpoint forwards requests to /v1/videos on the selected upstream provider.
• Mark a provider with the Videos toggle in admin so it can receive video-generation traffic.
• The endpoint rewrites the model to the upstream ID before proxying.