feat(microsoft-foundry/gpt-realtime-1.5): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for microsoft-foundry/gpt-realtime-1.5.

---

Note

Low Risk
Metadata-only YAML for a new model alias; no runtime or auth changes.

Overview
Adds a new Microsoft Foundry provider definition for gpt-realtime-1.5 as a serverless realtime model with text/image/audio input and text/audio output.

The entry documents token and audio pricing (including cache-read rates), limits (32k input / 4k output), capabilities (function calling, tool choice, prompt caching), and explicitly strips reasoning_effort via removeParams. Retirement is set to 2027-08-24, with links to Microsoft Learn and the Azure AI catalog.

^{Reviewed by Cursor Bugbot for commit ada5e15. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

/test-models

[cursor]

Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit ada5e15. Configure here.}

[cursor]

Missing image input cost

Medium Severity

The costs entry has no input_cost_per_image_token even though image is a listed input modality. Image tokens are billed at a different rate than text, so image turns will be costed incorrectly.

Additional Locations (1)

• providers/microsoft-foundry/gpt-realtime-1.5.yaml#L19-L23

 

^{Reviewed by Cursor Bugbot for commit ada5e15. Configure here.}

[LordGameleo]

Approving: bot-generated model addition. Required check (Validate YAML files) is green; the gateway-test trigger failure is a CI infra issue, not a model validation failure.