feat(openrouter/inclusionai/ling-3.0-flash-sante:free): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for openrouter/inclusionai/ling-3.0-flash-sante:free.

---

Note

Low Risk
Adds a static model definition only; no runtime, auth, or billing logic changes.

Overview
Adds OpenRouter provider metadata for inclusionai/ling-3.0-flash-sante:free, mirroring other Ling 3.0 free variants (e.g. ling-3.0-flash-fin:free).

The new entry marks the model active with zero token costs, 262k context / 32k max output, text chat mode, function calling and tool choice, serverless provisioning, and thinking: true.

^{Reviewed by Cursor Bugbot for commit fcfb503. 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 f2a0a44. Configure here.}

[cursor]

Missing max_tokens override

Medium Severity

This fuller YAML sets limits.max_output_tokens to 32768, above the inherited OpenRouter default.yaml params.max_tokens.maxValue of 4096, and does not add a model-level params.max_tokens override. Requests above 4096 stay capped below the advertised output limit.

 

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

^{Reviewed by Cursor Bugbot for commit f2a0a44. Configure here.}

[github-actions]

/test-models