fal.ai
Explore fal.ai models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
fal.aifal
No provider claim
| Provider | fal.ai |
|---|---|
| Routing status | Active |
| Provider website | https://fal.ai/ |
| Models | 2 public models |
| Credits routes | 2 |
| Zero data retention | not claimed |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | TrustedRouter supports bounded fal image generation and MiniMax H3 Max video generation with first-party pricing and paid generation canaries. H3 Max video is returned inline through fal's fixed queue host rather than a provider-selected download host. No contractual ZDR, confidential-compute, or E2EE claim is tracked. Policy source |
Measured performance
1 samplesContinuously sampled across fal.ai's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | — |
|---|---|
| Effective throughput | — |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| fal/flux-1-schnell | — | — | 100.00% | — | 1 |
fal.ai performance history · Full provider & model leaderboard.
Models served by fal.ai.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
fal/flux-1-schnellFLUX.1 Schnell on FAL |
— | 0 | selected route | Not published | selected route |
minimax/h3-maxMiniMax H3 Max |
— | 10,000 | selected route | Not published | selected route |
Questions
Does fal.ai have zero data retention?
TrustedRouter does not currently mark fal.ai as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is fal.ai end-to-end encrypted?
TrustedRouter does not currently mark fal.ai as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which fal.ai models are available through TrustedRouter?
This page currently lists 2 public fal.ai models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.