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

[harshiv-26]

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

---

Note

Low Risk
Low risk: only adds new Together AI model definition YAMLs with metadata and placeholder (0.0) token costs; no runtime logic changes.

Overview
Adds two new Together AI model definition YAMLs: pixverse/pixverse-v6 (text+image to video/audio, mode: video, status: active) and xai/grok-imagine-image-pro (text to image, mode: image). Both are marked serverless and include region-wide cost stubs (0.0) for token pricing.

^{Reviewed by Cursor Bugbot for commit 50501e0. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 2
• Passed: 0
• Failed: 0
• Validation failed: 0
• Errored: 0
• Skipped: 2
• Success rate: 0.0%

Provider	Model	Scenarios
together-ai	pixverse/pixverse-v6	skipped: skip-check
together-ai	xai/grok-imagine-image-pro	skipped: skip-check

Skipped (2)

together-ai/pixverse/pixverse-v6 — skip-check (skipped)

Skip reason:

unsupported mode 'video'

together-ai/xai/grok-imagine-image-pro — skip-check (skipped)

Skip reason:

unsupported mode 'image'

[cursor]

Cursor Bugbot has reviewed your changes and found 2 potential issues.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 50501e0. Configure here.}

[cursor]

Missing status field in model definition

Medium Severity

The grok-imagine-image-pro.yaml model definition is missing the status field. Every other active model in the together-ai provider includes status: active. The sibling file pixverse-v6.yaml added in the same commit correctly includes it. This omission could cause the model to be filtered out or behave unexpectedly in systems that rely on the status field to determine model availability.

 

^{Reviewed by Cursor Bugbot for commit 50501e0. Configure here.}

[cursor]

Suspicious audio output modality for video model

Low Severity

The pixverse-v6.yaml lists audio as an output modality alongside video. No other video generation model in the together-ai provider (including pixverse-v5 and pixverse-v5.6) lists audio as an output. Only dedicated text-to-speech models (e.g., cartesia/sonic-2) have audio as output. This is likely an error in the auto-generated model definition.

 

^{Reviewed by Cursor Bugbot for commit 50501e0. Configure here.}