Fix OpenAI provider compatibility with newer models

- Convert max_tokens to max_completion_tokens for all OpenAI API calls
- Remove temperature parameter for GPT-5 and o-series models (they only support default)
- Bump version to 0.1.2
- Update CHANGELOG with compatibility fixes

These changes ensure OneLLM works seamlessly with GPT-5, o1, o3, and future OpenAI models
while maintaining backward compatibility for existing code.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: ranaroussi

CHANGELOG.md

@@ -1,5 +1,23 @@
 # CHANGELOG
 
+## 0.1.2 - OpenAI Provider Compatibility Updates
+
+**Status**: Development Status :: 5 - Production/Stable
+
+### Bug Fixes
+
+- **OpenAI Provider Parameter Updates**: Fixed compatibility issues with newer OpenAI models
+  - Automatically converts `max_tokens` to `max_completion_tokens` for all OpenAI models
+  - Removes `temperature` parameter for GPT-5 and o-series models that only support default temperature
+  - Ensures compatibility with GPT-5, o1, o3, and future OpenAI model releases
+  - Backward compatible - existing code using `max_tokens` continues to work without changes
+
+### Technical Details
+
+- Models starting with `gpt-5` or `o` now have temperature parameter automatically removed
+- All OpenAI API calls now use `max_completion_tokens` instead of deprecated `max_tokens`
+- Changes are transparent to users - no code modifications required
+
 ## 0.1.1 - Moonshot Provider Addition
 
 **Status**: Development Status :: 5 - Production/Stable

onellm/.version

@@ -1 +1 @@
-0.1.1
+0.1.2

onellm/providers/openai.py

@@ -376,6 +376,14 @@ async def create_chat_completion(
         # Process messages for vision models if needed
         processed_messages = self._process_messages_for_vision(messages, model)
 
+        # Handle max_tokens -> max_completion_tokens renaming for OpenAI API
+        if "max_tokens" in kwargs:
+            kwargs["max_completion_tokens"] = kwargs.pop("max_tokens")
+
+        # Remove temperature for GPT-5 and o-series models that don't support it
+        if model.startswith("gpt-5") or model.startswith("o"):
+            kwargs.pop("temperature", None)
+
         # Set up the request data
         data = {
             "model": model,
@@ -573,6 +581,14 @@ async def create_completion(
         Returns:
             CompletionResponse or generator yielding completion chunks
         """
+        # Handle max_tokens -> max_completion_tokens renaming for OpenAI API
+        if "max_tokens" in kwargs:
+            kwargs["max_completion_tokens"] = kwargs.pop("max_tokens")
+
+        # Remove temperature for GPT-5 and o-series models that don't support it
+        if model.startswith("gpt-5") or model.startswith("o"):
+            kwargs.pop("temperature", None)
+
         # Prepare request data with all parameters
         request_data = {"model": model, "prompt": prompt, "stream": stream, **kwargs}