scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

fix: add cache read pricing for runinfra Qwen3.8-27B

Browse source 
Verified live on 2026-08-16: two identical 4,217 token prompts through the public endpoint, second response reported 4,160 cached prompt tokens; the model page lists $0.01 per million cached input tokens.
This commit is contained in:
jaberjaber23 2026-08-16 03:22:29 +03:00
parent 18690ea835
commit ee51908373
2 changed files with 4 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/model_prices_and_context_window_backup.json
View file

@ -48020,6 +48020,7 @@
"supports_tool_choice": true
},
"runinfra/Qwen/Qwen3.8-27B": {
"cache_read_input_token_cost": 1e-08,
"input_cost_per_token": 1e-07,
"litellm_provider": "runinfra",
"max_input_tokens": 262144,
@ -48033,6 +48034,7 @@
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true

2
model_prices_and_context_window.json
View file

@ -48020,6 +48020,7 @@
"supports_tool_choice": true
},
"runinfra/Qwen/Qwen3.8-27B": {
"cache_read_input_token_cost": 1e-08,
"input_cost_per_token": 1e-07,
"litellm_provider": "runinfra",
"max_input_tokens": 262144,
@ -48033,6 +48034,7 @@
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true