Inferless
AutomatedServerless GPU platform for deploying ML models with pay-per-second pricing.
Inferless has 2 plans: paid plans from $0.0006 and custom pricing for larger teams. The last price change we recorded was on 16 September 2026.
Inferless plans and prices
Starter
usage based$0.0006
$0.000555/sec
- Target Audience — Small teams and independent developers
- Free Credit — 10 hours of free credit
Enterprise
Custom
- Built for fast-growing startups and larger organizations — Looking to scale quickly at an affordable cost with desired latency results.
- Inference Requests — Min 100,000 Inference Requests per month
- Deployed Webhook Endpoints — Unlimited deployed webhook endpoints
- GPU Concurrency — 50
- Log Retention — 365 day of log retention
- Support — Support via private Slack connect & support engineer
- Credits — Custom
Price history
Last 5 recorded changes
| Date | Plan | Change | Old | New | Δ% |
|---|---|---|---|---|---|
| Sep 16, 2026 | Starter | Decrease | $0.0006 | $0.0006 | -7.5% |
| Sep 12, 2026 | Starter | Decrease | $0.0006 | $0.0006 | -7.5% |
| Sep 7, 2026 | Starter | Decrease | $0.0006 | $0.0006 | -7.5% |
| Jul 28, 2026 | Enterprise | Reclassified | $0 | — | — |
| Jul 28, 2026 | Starter | Decrease | $0.0006 | $0.0006 | -7.5% |
Other AI & ML products
No confirmed alternatives yet.