fal video models vs PixVerse API

fal video models

One key and one queue API reach 137 active text-to-video endpoints, each with a published price, an OpenAPI document and an llms.txt. Billing units, duration formats and audio pricing differ per model, there is no free tier, and a person must sign up in a browser and buy credit.

PixVerse API

V6 at about $0.04 a second at 720p, with audio and clips up to 15 seconds. Plan prices and the dollar value of a credit sit on a JavaScript-only billing page.

fal video models

1. Submit to queue.fal.run, keep the request_id, then poll status_url or set fal_webhook. Never resubmit to check progress, because each submit is a new billable job
2. Read https://fal.ai/models/<endpoint-id>/llms.txt before a call. duration is the string "5" on Kling, "8s" on Veo 3.1 and an integer on Wan 3.0
3. Set generate_audio on purpose. It defaults to true and raises the Kling v3 Pro price from $0.112 to $0.168 a second and Veo 3.1 from $0.20 to $0.40
4. Check metadata.status in https://api.fal.ai/v1/models before pinning an endpoint. Deprecated endpoints carry no removal date
5. Use an API-scope key, never an ADMIN key. A new account runs 2 requests at once, so long video jobs queue behind each other
6. The MCP relay has no server-side approval gate. Call get_pricing and get the owner's approval before submit_job

PixVerse API

1. Generate a new UUID for Ai-trace-id on every new submit. Reuse it only to fetch the same job again
2. Poll the result endpoint. Status 1 is done, 5 generating, 7 moderation failure, 8 failed
3. Moderate prompts before calling. Repeated status 7 results can suspend the key
4. Use model v6 or c1 for new work. Older model tables still sit in the docs