fal video models vs framefields

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.

framefields

A free Apache-2.0 library that renders video from TypeScript on the GPU, with lint and QA codes an agent can act on. It is fifteen days old, called beta, and its Claude Code install command names a plugin directory entry that was not found on 20 October 2026.

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

framefields

1. Add the plugin with /plugin marketplace add gatewai-dev/framefields first; the official-directory install was not found on 20 October 2026.
2. Approve only the skia-canvas install script, as the getting-started page shows, or imports fail with a missing skia.node.
3. Check with comp.lint() and renderFrameGrid before a full renderVideo encode.
4. Call process.exit() after rendering; native GPU threads keep the script alive.
5. Preload vision models into FRAMEFIELDS_MODELS_DIR for offline or CI renders.