tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-23 18:25:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: correct Groq gpt-oss pricing and add cache pricing (#19311)

Browse Source
This commit is contained in:
Connor Luebbehusen
2026-01-19 10:41:28 -08:00
committed by GitHub
parent 608979c7e9
commit 2ba7d2e821
2 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/model_prices_and_context_window_backup.json
+5 -3
View File
@@ -18826,13 +18826,14 @@
"supports_tool_choice": true
},
"groq/openai/gpt-oss-120b": {
"cache_read_input_token_cost": 7.5e-08,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "groq",
"max_input_tokens": 131072,
"max_output_tokens": 32766,
"max_tokens": 32766,
"mode": "chat",
"output_cost_per_token": 7.5e-07,
"output_cost_per_token": 6e-07,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_reasoning": true,
@@ -18841,13 +18842,14 @@
"supports_web_search": true
},
"groq/openai/gpt-oss-20b": {
"input_cost_per_token": 1e-07,
"cache_read_input_token_cost": 3.75e-08,
"input_cost_per_token": 7.5e-08,
"litellm_provider": "groq",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 5e-07,
"output_cost_per_token": 3e-07,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_reasoning": true,
model_prices_and_context_window.json
+5 -3
View File
@@ -18826,13 +18826,14 @@
"supports_tool_choice": true
},
"groq/openai/gpt-oss-120b": {
"cache_read_input_token_cost": 7.5e-08,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "groq",
"max_input_tokens": 131072,
"max_output_tokens": 32766,
"max_tokens": 32766,
"mode": "chat",
"output_cost_per_token": 7.5e-07,
"output_cost_per_token": 6e-07,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_reasoning": true,
@@ -18841,13 +18842,14 @@
"supports_web_search": true
},
"groq/openai/gpt-oss-20b": {
"input_cost_per_token": 1e-07,
"cache_read_input_token_cost": 3.75e-08,
"input_cost_per_token": 7.5e-08,
"litellm_provider": "groq",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 5e-07,
"output_cost_per_token": 3e-07,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_reasoning": true,