o4-mini, closes #976

docs/openai-models.md

@@ -58,6 +58,7 @@ OpenAI Chat: o1-preview
 OpenAI Chat: o1-mini
 OpenAI Chat: o3-mini
 OpenAI Chat: o3
+OpenAI Chat: o4-mini
 OpenAI Completion: gpt-3.5-turbo-instruct (aliases: 3.5-instruct, chatgpt-instruct)
 ```
 <!-- [[[end]]] -->

docs/usage.md

@@ -935,6 +935,25 @@ OpenAI Chat: o3
   Keys:
     key: openai
     env_var: OPENAI_API_KEY
+OpenAI Chat: o4-mini
+  Options:
+    temperature: float
+    max_tokens: int
+    top_p: float
+    frequency_penalty: float
+    presence_penalty: float
+    stop: str
+    logit_bias: dict, str
+    seed: int
+    json_object: boolean
+    reasoning_effort: str
+  Features:
+  - streaming
+  - schemas
+  - async
+  Keys:
+    key: openai
+    env_var: OPENAI_API_KEY
 OpenAI Completion: gpt-3.5-turbo-instruct (aliases: 3.5-instruct, chatgpt-instruct)
   Options:
     temperature: float

llm/default_plugins/openai_models.py

@@ -121,6 +121,10 @@ def register_models(register):
         Chat("o3", reasoning=True, supports_schema=True),
         AsyncChat("o3", reasoning=True, supports_schema=True),
     )
+    register(
+        Chat("o4-mini", reasoning=True, supports_schema=True),
+        AsyncChat("o4-mini", reasoning=True, supports_schema=True),
+    )
     # The -instruct completion model
     register(
         Completion("gpt-3.5-turbo-instruct", default_max_tokens=256),