-
Notifications
You must be signed in to change notification settings - Fork 37
Open
Description
Hello.
Could the SDK expose the rate limit information which is part of the response headers?
> POST /v1/chat/completions HTTP/2
> Host: api.mistral.ai
> User-Agent: curl/8.7.1
> Accept: */*
> Content-Type: application/json
> Authorization: Bearer qN7h6rEWlmjs5iL67Y4rtladP3P76C2t
> Content-Length: 135
...
< x-ratelimit-limit-tokens-minute: 5000000
< x-ratelimit-remaining-tokens-minute: 4999911
< x-ratelimit-tokens-query-cost: 52
< x-ratelimit-limit-req-minute: 720
< x-ratelimit-remaining-req-minute: 717
Like:
- x-ratelimit-limit-tokens-minute
- x-ratelimit-remaining-tokens-minute
- x-ratelimit-limit-req-minute
- x-ratelimit-remaining-req-minute
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels