Getting Started
Rate Limits
Getting Started
Rate Limits
Perplexity Sonar Models
| Model | Request Rate Limit |
|---|---|
llama-3.1-sonar-small-128k-online | 50/min |
llama-3.1-sonar-large-128k-online | 50/min |
llama-3.1-sonar-huge-128k-online | 50/min |
Perplexity Chat Models
| Model | Request Rate Limit |
|---|---|
llama-3.1-sonar-small-128k-chat | 50/min |
llama-3.1-sonar-large-128k-chat | 50/min |
Open Source Models
| Model | Request rate limit |
|---|---|
llama-3.1-8b-instruct | - 100/min |
llama-3.1-70b-instruct | - 60/min |
We limit model usage if the request rate exceeds the limit for any given model.
To request elevated rate limits, fill out this form.