feat(openrouter/openai/gpt-6-astra:batch): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for openrouter/openai/gpt-6-astra:batch.

---

Note

Low Risk
Adds catalog metadata only; no runtime, auth, or application logic changes.

Overview
Registers openai/gpt-6-astra:batch on OpenRouter via a new provider YAML (auto-generated model-addition).

The entry defines serverless chat pricing (including prompt-cache read/write token costs), a 1.05M context window, 128k max output, thinking enabled, and inputs text, image, and PDF. Capabilities include function calling, JSON/structured output, tool choice, and prompt caching.

^{Reviewed by Cursor Bugbot for commit 9995700. Bugbot is set up for automated code reviews on this repo. Configure here.}

[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 e567238. Configure here.}

[cursor]

Inherited max_tokens cap too low

Medium Severity

This fuller entry sets limits.max_output_tokens to 128000, above the inherited OpenRouter params.max_tokens.maxValue of 4096, and does not override params.max_tokens. Callers can be capped at 4096 output tokens instead of the advertised limit.

 

^{Triggered by learned rule: Override max_tokens maxValue to match limits}

^{Reviewed by Cursor Bugbot for commit e567238. Configure here.}

[github-actions]

/test-models