Greetings @frankc , 

The Responses API is not currently supported for gpt-oss models (or any models) on Databricks Foundation Model APIs, despite OpenAI stating that gpt-oss models are compatible with it. This is a platform limitation specific to Databricks' implementation, not a model limitation.

Why the Responses API Isn't Available

Databricks Foundation Model APIs are designed to be OpenAI-compatible, but they currently only support the Chat Completions API endpoint (`/v1/chat/completions`), not the newer Responses API endpoint (`/v1/responses`). When Databricks hosts models through their Foundation Model serving infrastructure, they implement specific API endpoints, and the Responses API simply hasn't been added to their supported endpoint types yet.

Key Differences Between the APIs

The Responses API is OpenAI's newer interface that offers:

- Native conversation state management: Automatically stores conversation history using `previous_response_id` instead of requiring you to manually pass message arrays
- Simplified input format: Uses `input` parameter instead of `messages` array
- First-class tool support: Better integration for agentic workflows
- Built-in storage: Responses are stored by default for easy retrieval

The Chat Completions API requires you to manually manage conversation state by passing the full message history with each request.

Current Workarounds

Since the Responses API isn't available on Databricks, you'll need to continue using the Chat Completions API:

```python
from openai import OpenAI
import os

client = OpenAI(
api_key=os.environ.get('DATABRICKS_TOKEN'),
base_url="https://your-workspace.cloud.databricks.com/serving-endpoints"
)

response = client.chat.completions.create(
model="databricks-gpt-oss-20b",
messages=[
{"role": "user", "content": "Your prompt here"}
],
max_tokens=5000
)
```

When Will It Be Available?

There's no official timeline from Databricks for Responses API support. This appears to be a feature request that the community has raised. If you need the Responses API specifically, your options are:

- Use OpenAI directly: Create an external model serving endpoint pointing to OpenAI's API (though this means data leaves Databricks)
- Use alternative cloud providers: Cloudflare Workers AI reportedly supports the Responses API for gpt-oss models, though with limitations on rate limits and file sizes
- Wait for Databricks implementation: Continue monitoring Databricks announcements and community forums

You may want to upvote or add your use case to the community forum thread to help prioritize this feature with Databricks engineering.

Hope this helps, Louis.