Serverless generative media — fast hosting for FLUX, Recraft, and Ideogram image models.
fal is a serverless inference platform specialised in generative media — image and video models served at low latency, including the FLUX family from Black Forest Labs, Recraft, and Ideogram. US-hosted; fal does not train on customer data, and zero data retention is available via Opper Enterprise contract. The route to pick when you want fast, scalable image generation across multiple frontier media model families under one API.
Every model we route through fal. Compare residency, ZDR, training posture, and price at a glance — full data-handling detail per route below.
| Model | Region | Zero data retention | Training | Context | Input | Output |
|---|---|---|---|---|---|---|
| US | Enterprise | No | — | — | — | |
| US | Enterprise | No | — | — | — | |
| US | Enterprise | No | — | — | — | |
| US | Enterprise | No | — | — | — | |
| US | Enterprise | No | — | — | — | |
| US | Enterprise | No | — | — | — | |
Ideogram V3 Ideogram | US | Enterprise | No | — | — | — |
Recraft V3 Recraft | US | Enterprise | No | — | — | — |
Recraft V3 Recraft | US | Enterprise | No | — | — | — |
fal hosts on 1 route. Each route has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
