phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

docs

Browse source
This commit is contained in:
ishaan-jaff 2023-09-16 13:01:11 -07:00
parent ed94410ef5
commit 33693615ed
1 changed files with 14 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

18
docs/my-website/docs/max_tokens_cost.md
View file

@ -1,16 +1,16 @@
# /get model context window & cost per token # get context window & cost per token
For every LLM LiteLLM allows you to: For every LLM LiteLLM allows you to:
* Get model context window * Get model context window
* Get cost per token * Get cost per token
## LiteLLM API api.litellm.ai ## using api.litellm.ai
Usage Usage
```curl ```curl
curl 'https://api.litellm.ai/get_max_tokens?model=claude-2' curl 'https://api.litellm.ai/get_max_tokens?model=claude-2'
``` ```
### Output ### output
```json ```json
{ {
"input_cost_per_token": 1.102e-05, "input_cost_per_token": 1.102e-05,
@ -20,9 +20,19 @@ curl 'https://api.litellm.ai/get_max_tokens?model=claude-2'
} }
``` ```
## LiteLLM Package ## using the litellm python package
Usage Usage
```python ```python
import litellm import litellm
model_data = litellm.model_cost["gpt-4"] model_data = litellm.model_cost["gpt-4"]
``` ```
### output
```json
{
"input_cost_per_token": 3e-06,
"max_tokens": 8192,
"model": "gpt-4",
"output_cost_per_token": 6e-05
}
```