feat(microsoft-foundry/gpt-6-astra): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for microsoft-foundry/gpt-6-astra.

---

Note

Low Risk
Adds static model metadata only; no runtime or auth logic changes.

Overview
Adds a new Microsoft Foundry model definition for gpt-6-astra so routing, pricing, and capability metadata can treat it as an active serverless chat model.

The entry documents global and datazone_us token costs (including prompt-cache read/write) with cumulative tiered pricing above 272k tokens, ~1.05M context / 128k max output, and text + image input. It flags thinking, tool/function calling, structured/JSON output, and reasoning_effort (default medium) while stripping temperature, top_p, and max_tokens in favor of max_completion_tokens.

^{Reviewed by Cursor Bugbot for commit f038de4. 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 f038de4. Configure here.}

[cursor]

Unsupported reasoning_effort value listed

Medium Severity

reasoning_effort supportedValues includes none, which this model does not accept. Official GPT-6 Astra docs and the same-catalog gpt-6-astra-2026-09-03-private entry list only low, medium, high, xhigh, and max. Callers that send none will get rejected by the API.

 

^{Reviewed by Cursor Bugbot for commit f038de4. Configure here.}