github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-03 11:47:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

community: Add cost per 1K tokens for fine-tuned model cached input (#29248)

Browse Source 
### Description

- Since there is no cost per 1k input tokens for a fine-tuned cached
version of `gpt-4o-mini-2024-07-18` is not available when using the
`OpenAICallbackHandler`, it raises an error when trying to make calls
with such model.
- To add the price in the `MODEL_COST_PER_1K_TOKENS` dictionary

cc. @efriis
This commit is contained in:
Luis Lopez 2025-01-16 21:19:26 +01:00 committed by GitHub
parent 667d2a57fd
commit 75663f2cae
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
libs/community/langchain_community/callbacks/openai_info.py
View File

@ -128,6 +128,7 @@ MODEL_COST_PER_1K_TOKENS = {
"gpt-3.5-turbo-1106-finetuned": 0.003, "gpt-3.5-turbo-1106-finetuned": 0.003,
"gpt-3.5-turbo-0125-finetuned": 0.003, "gpt-3.5-turbo-0125-finetuned": 0.003,
"gpt-4o-mini-2024-07-18-finetuned": 0.0003, "gpt-4o-mini-2024-07-18-finetuned": 0.0003,
"gpt-4o-mini-2024-07-18-finetuned-cached": 0.00015,
# Fine Tuned output # Fine Tuned output
"babbage-002-finetuned-completion": 0.0016, "babbage-002-finetuned-completion": 0.0016,
"davinci-002-finetuned-completion": 0.012, "davinci-002-finetuned-completion": 0.012,