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

docs(token_usage.md): fix completion cost docs

Browse source
This commit is contained in:
Krrish Dholakia 2023-10-21 16:15:04 -07:00
parent 5ac497c56b
commit c300ab45d4
1 changed files with 9 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -95,9 +95,10 @@ print(prompt_tokens_cost_usd_dollar, completion_tokens_cost_usd_dollar)
### 5. `completion_cost`
* Input: Accepts a `litellm.completion()` response
* Input: Accepts a `litellm.completion()` response **OR** prompt + completion strings
* Output: Returns a `float` of cost for the `completion` call
**litellm.completion()**
```python
from litellm import completion, completion_cost
@ -112,6 +113,13 @@ formatted_string = f"${float(cost):.10f}"
print(formatted_string)
```
**prompt + completion string**
```python
from litellm import completion_cost
cost = completion_cost(prompt="Hey!", completion="How's it going?")
formatted_string = f"${float(cost):.10f}"
print(formatted_string)
```
### 6. `get_max_tokens`
* Input: Accepts a model name - e.g. `gpt-3.5-turbo` (to get a complete list, call `litellm.model_list`)