mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-17 09:34:48 +00:00
fix(zerogpu): flag tools, json_schema and prompt caching on gpt-6-luna
ZeroGPU serves function calling, tool_choice, json_schema response_format and prompt caching on gpt-6-luna, so set supports_function_calling, supports_tool_choice, supports_response_schema and supports_prompt_caching on its row in both cost maps. Checked live on 2026-10-28, a weather tool call came back with the right arguments, json_schema output validated, and repeated prompts reported 3260 of 3263 tokens cached
This commit is contained in:
parent
25d56024f9
commit
ace778d011
2 changed files with 10 additions and 2 deletions
|
|
@ -65360,7 +65360,11 @@
|
|||
"mode": "chat",
|
||||
"output_cost_per_token": 5e-07,
|
||||
"source": "https://docs.zerogpu.ai/docs/model-catalog",
|
||||
"supports_reasoning": true
|
||||
"supports_function_calling": true,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"zerogpu/gpt-oss-120b": {
|
||||
"cache_read_input_token_cost": 3e-08,
|
||||
|
|
|
|||
|
|
@ -65360,7 +65360,11 @@
|
|||
"mode": "chat",
|
||||
"output_cost_per_token": 5e-07,
|
||||
"source": "https://docs.zerogpu.ai/docs/model-catalog",
|
||||
"supports_reasoning": true
|
||||
"supports_function_calling": true,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"zerogpu/gpt-oss-120b": {
|
||||
"cache_read_input_token_cost": 3e-08,
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue