feat: added o4-mini support (#221)

Author: MiNeves00

examples/core.py

@@ -113,7 +113,7 @@ async def async_stream():
     return latencies
 
 def build_chat_request(model: str, chat_input: str, is_stream: bool, max_tokens: int=1000):
-    if model.startswith(('o1', 'o3')):
+    if model.startswith(('o1', 'o3', 'o4')):
         chat_request = {
             "chat_input": chat_input,
             "model": model,
@@ -156,7 +156,7 @@ def multiple_provider_runs(provider:str, model:str, num_runs:int, api_key:str, *
 def run_chat_all_providers():    
     # OpenAI
     multiple_provider_runs(provider="openai", model="gpt-4o-mini", api_key=os.environ["OPENAI_API_KEY"], num_runs=1)
-    multiple_provider_runs(provider="openai", model="o3-mini", api_key=os.environ["OPENAI_API_KEY"], num_runs=1)
+    multiple_provider_runs(provider="openai", model="o4-mini", api_key=os.environ["OPENAI_API_KEY"], num_runs=1)
     #multiple_provider_runs(provider="openai", model="o1-preview", api_key=os.environ["OPENAI_API_KEY"], num_runs=1)
 
 

libs/core/llmstudio_core/config.yaml

@@ -238,6 +238,12 @@ providers:
         input_token_cost: 0.0000011
         cached_token_cost: 0.00000055
         output_token_cost: 0.0000044
+      o4-mini:
+        mode: chat
+        max_completion_tokens: 200000
+        input_token_cost: 0.0000011
+        cached_token_cost: 0.000000275
+        output_token_cost: 0.0000044
       gpt-4o-mini:
         mode: chat
         max_tokens: 128000