phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-24 18:24:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(docs) upperbound_key_generate_params

Browse source
This commit is contained in:
ishaan-jaff 2024-02-05 22:37:05 -08:00
parent 7a0bccf4d0
commit d4fd287617
2 changed files with 18 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

16
docs/my-website/docs/proxy/virtual_keys.md
View file

@ -352,6 +352,22 @@ Request Params:
}
```
## Upperbound /key/generate params
Use this, if you need to control the upperbound that users can use for `max_budget`, `budget_duration` or any `key/generate` param per key.
Set `litellm_settings:upperbound_key_generate_params`:
```yaml
litellm_settings:
upperbound_key_generate_params:
max_budget: 100 # upperbound of $100, for all /key/generate requests
duration: "30d" # upperbound of 30 days for all /key/generate requests
```
** Expected Behavior **
- Send a `/key/generate` request with `max_budget=200`
- Key will be created with `max_budget=100` since 100 is the upper bound
## Default /key/generate params
Use this, if you need to control the default `max_budget` or any `key/generate` param per key.

4
litellm/model_prices_and_context_window_backup.json
View file

@ -156,8 +156,8 @@
"max_tokens": 4097,
"max_input_tokens": 4097,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000012,
"output_cost_per_token": 0.000016,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000006,
"litellm_provider": "openai",
"mode": "chat"
},