Rate limits

Rate limits serve as essential mechanisms to control the flow of requests made to a system, ensuring its stability and fair usage. They impose restrictions on the number of requests that can be made within a specific time frame. Rate limits are commonly measured in terms of RPM (requests per minute) or RPS (requests per second), indicating the maximum allowed number of requests a user or application can make during that time.

Below are the rate limits for all of our models. If you require a higher limit for your particular use case, please don't hesitate to get in touch with us at [email protected].

Foundation models - Jurassic-2

In the case of our foundation models, there are limits per second (RPS) and per minute (RPM):

Foundation Model	RPS	RPM
Jurassic-2 Light	20	480
Jurassic-2 Mid	20	480
Jurassic-2 Ultra	5	180

In the case of custom models, there are limits per second (RPS) and per minute (RPM) (depending on the base model):

Custom Model (Based on):	RPS	RPM
Jurassic-2 Light	20	480
Jurassic-2 Mid	20	480
Jurassic-2 Ultra	5	180

Task-specific Models

For the task-specific models, there are only limitations per minute:

Task-specific Model	RPM
Paraphrase	30
Grammatical Error Correction (GEC)	100
Text Improvements	30
Summarize	30
Summarize by Segment	30
Text Segmentation	200
Contextual Answers	100
Semantic Search	100
Embeddings	30
Document Library (upload)	100