Propose an edit — Fal.ai
Anything look wrong? Fix it. Proposals are queued for an editor — approved corrections are applied to the entry and recorded in the public journal.
edit_proposal — fal-ai
// sign in to propose edits
Edits are tied to accounts so reviewers can weigh evidence and reward useful contributions. Proposals are queued — an editor reviews every change before it is applied.
- name
- Fal.ai
- domain
- fal.ai
- category
- Paid API
- free tier
- yes
- free credits
- — not quantified — No free tier stated on official pages (checked 2026-09-16): fal.ai/pricing and the Model APIs pricing docs describe only prepaid credits, with no starter credit or free allowance.
- description
- fal.ai runs a generative-media model API: 1,000+ endpoints across image, video, audio and 3D behind one queue-based HTTP interface, called with the same request/response shape from Python, JavaScript or raw HTTP. Pricing is per output rather than per token, as published on its pricing page: $0.03 per Seedream V4 image, $0.04 per Flux Kontext Pro image, $0.02 per megapixel for Qwen image, $0.05 per second of Wan 2.5 video, $0.07 per second of Kling 2.5 Turbo Pro and $0.40 per second of Veo 3 video. Dedicated GPU capacity is listed at $4.50/hr for H100 (as low as $1.89/hr), $4.50/hr for H200, $6.25/hr for B200 and $8.50/hr for B300. There is no free token allowance: fal runs on a prepaid credit balance that funds both model usage and the account's concurrency limit.
how this works
- 01. Only the fields below can be changed — pricing tables, models and risk reviews stay with editors.
- 02. Changes to data fields (description, category, free tier, credit values) require a rationale or source link.
- 03. Max 3 open proposals per account. Approved edits are published and logged in the public journal.
- 04. Current category: Paid API — the entry currently reports a free tier.