scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 87

fix: correct token limits for Kimi K2.5 and MiniMax M2.5

Browse source 
Kimi K2.5: max_output_tokens was 262K (exceeding 131K context window).
Corrected to 8K max output per actual model spec.

MiniMax M2.5: max_output_tokens was 131K but actual max output is 16K.
Kept max_input_tokens at 1M (correct context window).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Kyle D 2026-04-03 10:34:09 +01:00
parent fefe6b3f84
commit 3cd359d1c7
1 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
model_prices_and_context_window.json
View file

@ -293,9 +293,9 @@
"source": "https://avian.io"
},
"avian/moonshotai/kimi-k2.5": {
"max_tokens": 262144,
"max_tokens": 8192,
"max_input_tokens": 131072,
"max_output_tokens": 262144,
"max_output_tokens": 8192,
"input_cost_per_token": 4.5e-07,
"output_cost_per_token": 2.2e-06,
"litellm_provider": "avian",
@ -317,9 +317,9 @@
"source": "https://avian.io"
},
"avian/minimax/minimax-m2.5": {
"max_tokens": 131072,
"max_tokens": 16384,
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"max_output_tokens": 16384,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 1.1e-06,
"litellm_provider": "avian",