feat(openrouter/~z-ai/glm-flash-latest): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for openrouter/~z-ai/glm-flash-latest.

---

Note

Low Risk
Adds a static model metadata file only; no runtime logic, auth, or data-handling changes.

Overview
Adds a new OpenRouter provider definition for ~z-ai/glm-flash-latest, enabling routing to the Z-AI GLM Flash model with chat mode, serverless provisioning, and OpenRouter as the source.

The config sets token pricing (including prompt-cache read cost), a 1.3M context window, 131K max output, and capabilities such as function calling, JSON/structured output, tool choice, and thinking: true. Compared to the existing glm-latest entry, this variant also advertises image and video input modalities alongside text.

^{Reviewed by Cursor Bugbot for commit 4d6ce0a. 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 2cea275. Configure here.}

[cursor]

Inherited reasoning effort default unsupported

Medium Severity

This thinking GLM-5.3-Flash alias inherits OpenRouter's reasoning_effort default of medium, which the model does not accept. Sibling GLM-5.3 entries set supportedValues to low, high, and max with default max, and dropping the param would hide a supported control.

 

^{Triggered by learned rule: Override inherited reasoning_effort when default isn't supported}

^{Reviewed by Cursor Bugbot for commit 2cea275. Configure here.}

[github-actions]

/test-models