Rate Limits

API Methods

Chat

`goodfire.client.chat.completions`

.create()
- Default 100 requests per minute, can request increase
- Default 50000 tokens per minute, can request increase

Attribution & Features

`goodfire.client.features`

.inspect()
- 300 requests per minute
.contrast()
- 100 requests per minute
.list()
- 500 requests per minute
.search()
- 500 requests per minute
.rerank()
- 500 requests per minute

`goodfire.client._experimental.features`

.neighbors()
- 100 requests per minute
.dimension_reduction()
- 30 requests per minute

Model Variants

`goodfire.client.variants`

.create()
- 500 requests per minute
.list()
- 500 requests per minute
.get()
- 500 requests per minute
.delete()
- 500 requests per minute
.update()
- 500 requests per minute

Organization Controls

Each organization has:

Maximum chat tokens per minute and maximum requests per minute
Credit balance system

Error Responses

The API will return errors when:

Rate limits are exceeded (429 Too Many Requests)
Organization has insufficient credits
Request exceeds organization token limits