Choose the plan that fits your AI inference needs. Scale up or down anytime.
Perfect for small projects and experimentation.
For growing businesses with production needs.
For large-scale deployments with custom needs.
An inference request is counted each time you successfully call our API to process input data using any of our models and receive a prediction or result. Failed requests or errors do not count towards your usage.
Yes, you can upgrade or downgrade your plan at any time through your account dashboard. Changes will be prorated for the current billing cycle.
For inference requests, we offer overage charges at a competitive rate per request once you exceed your plan's monthly limit. For other limits like concurrent requests, you may experience throttling. We recommend upgrading if you consistently exceed limits.
Yes! We offer a 14-day free trial of the Professional plan, including access to all models and a generous request limit. No credit card is required to start.