mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-06 08:16:43 +00:00
[Update] Adjust max_input_tokens for azure/gpt-5-chat models in JSON configuration
* Reduced max_input_tokens from 400000 to 272000 for both azure/gpt-5-chat and azure/gpt-5-chat-latest to optimize resource usage and align with updated model specifications.
This commit is contained in:
parent
b78495d398
commit
790d2d0830
2 changed files with 4 additions and 4 deletions
|
|
@ -2457,7 +2457,7 @@
|
|||
},
|
||||
"azure/gpt-5-chat": {
|
||||
"max_tokens": 128000,
|
||||
"max_input_tokens": 400000,
|
||||
"max_input_tokens": 272000,
|
||||
"max_output_tokens": 128000,
|
||||
"input_cost_per_token": 1.25e-06,
|
||||
"output_cost_per_token": 1e-05,
|
||||
|
|
@ -2490,7 +2490,7 @@
|
|||
},
|
||||
"azure/gpt-5-chat-latest": {
|
||||
"max_tokens": 128000,
|
||||
"max_input_tokens": 400000,
|
||||
"max_input_tokens": 272000,
|
||||
"max_output_tokens": 128000,
|
||||
"input_cost_per_token": 1.25e-06,
|
||||
"output_cost_per_token": 1e-05,
|
||||
|
|
|
|||
|
|
@ -2457,7 +2457,7 @@
|
|||
},
|
||||
"azure/gpt-5-chat": {
|
||||
"max_tokens": 128000,
|
||||
"max_input_tokens": 400000,
|
||||
"max_input_tokens": 272000,
|
||||
"max_output_tokens": 128000,
|
||||
"input_cost_per_token": 1.25e-06,
|
||||
"output_cost_per_token": 1e-05,
|
||||
|
|
@ -2490,7 +2490,7 @@
|
|||
},
|
||||
"azure/gpt-5-chat-latest": {
|
||||
"max_tokens": 128000,
|
||||
"max_input_tokens": 400000,
|
||||
"max_input_tokens": 272000,
|
||||
"max_output_tokens": 128000,
|
||||
"input_cost_per_token": 1.25e-06,
|
||||
"output_cost_per_token": 1e-05,
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue