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

[hganwani-droid]

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

---

Note

Low Risk
Low risk metadata-only changes, but incorrect supportedModes/mode values could affect model discovery/routing or UI filtering for Together AI models.

Overview
Adds/updates Together AI provider model manifests, primarily by introducing supportedModes across many existing image/chat/video/audio/embedding models to make mode support explicit.

Also adjusts several model metadata fields (notably limits.context_window values and a few model identifiers) and adds a batch of new minimal YAML entries for additional models that currently declare mode: unknown.

^{Written by Cursor Bugbot for commit def9208. This will update automatically on new commits. 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.}

[cursor]

Model ID org prefix capitalization mismatch

Medium Severity

The file resides in the salesforce/ directory, but the model field uses Salesforce/Llama-Rank-V1 (capital S). Every other file in this directory uses lowercase salesforce/ as the org prefix (e.g., salesforce/sarvam-m, salesforce/texteval-v3-7b-qwen-b). If the system derives or validates the org prefix from the directory name, this capitalization mismatch will cause a routing or lookup failure for this model.