Skip to main content

Frequently Asked Questions

1. How can I create an API key and use it with the models?​

You can create an API key at My Account → My API Keys. This key is required to call models via the inference API.

2. How is the model usage price calculated?​

Pricing is based on the number of input tokens and output tokens. You can view details at Product Information → Pricing or in Billing Management inside My Account.

3. What is the rate limit when using a model?​

Each model has its own rate limit (for example, requests per second or tokens per second). You can view this information at Product Information → Rate Limit.

4. Does the Marketplace support autoscaling for model endpoints?​

Yes. Endpoints can be configured with autoscaling based on traffic, optimizing costs while maintaining stability during traffic spikes.

Last updated on by Dang Tran