feat(together-ai): add new models [bot]

[harshiv-26]

Auto-generated by model-addition-agent for provider together-ai.

---

Note

Low Risk
Adds new YAML model metadata only; no runtime logic changes, with minimal risk aside from potential misconfiguration of model/cost fields.

Overview
Adds two new Together AI model definition files for vidu/vidu-q3 and vidu/vidu-q3-turbo.

Both models are registered as video-capable via supportedModes: [video], with placeholder metadata (mode: unknown) and zeroed token costs for all regions.

^{Reviewed by Cursor Bugbot for commit 4219ff4. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes 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 4219ff4. Configure here.}

[cursor]

Video models use wrong cost structure with zero values

Medium Severity

Both new files use per-token cost fields (input_cost_per_token: 0, output_cost_per_token: 0), while sibling vidu video models use input_cost_per_request or input_cost_per_image with real prices. This means costs will always compute to zero and the pricing model type is wrong for video generation.

Additional Locations (1)

• providers/together-ai/vidu/vidu-q3.yaml#L1-L4

 

^{Reviewed by Cursor Bugbot for commit 4219ff4. Configure here.}