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

docs update

Browse source
This commit is contained in:
ishaan-jaff 2023-09-06 17:21:55 -07:00
parent bd77d5ac21
commit a948e3ac89
1 changed files with 6 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

10
docs/my-website/docs/token_usage.md
View file

@ -11,7 +11,7 @@ However, we also expose 3 public helper functions to calculate token usage acros
## Example Usage ## Example Usage
1. `token_counter` ### 1. `token_counter`
```python ```python
from litellm import token_counter from litellm import token_counter
@ -20,7 +20,7 @@ messages = [{"user": "role", "content": "Hey, how's it going"}]
print(token_counter(model="gpt-3.5-turbo", messages=messages)) print(token_counter(model="gpt-3.5-turbo", messages=messages))
``` ```
2. `cost_per_token` ### 2. `cost_per_token`
```python ```python
from litellm import cost_per_token from litellm import cost_per_token
@ -32,8 +32,10 @@ prompt_tokens_cost_usd_dollar, completion_tokens_cost_usd_dollar = cost_per_toke
print(prompt_tokens_cost_usd_dollar, completion_tokens_cost_usd_dollar) print(prompt_tokens_cost_usd_dollar, completion_tokens_cost_usd_dollar)
``` ```
3. `completion_cost` ### 3. `completion_cost`
Accepts a `litellm.completion()` response and return a `float` of cost for the `completion` call
* Input: Accepts a `litellm.completion()` response
* Output: Returns a `float` of cost for the `completion` call
```python ```python
from litellm import completion, completion_cost from litellm import completion, completion_cost