feat(deepinfra/meta-models/Muse-Glimmer-30B): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for deepinfra/meta-models/Muse-Glimmer-30B.

---

Note

Low Risk
Adds static model metadata for one DeepInfra model with no changes to auth, billing execution, or application code paths.

Overview
Registers DeepInfra model meta-models/Muse-Glimmer-30B via a new file at providers/deepinfra/meta-models/Muse-Glimmer-30B.yaml.

The entry defines per-token costs (including prompt caching read pricing), a 131072 context and max output window, image input modality, and mode: unknown. It is a catalog/metadata addition only—no runtime or routing logic changes in this diff.

^{Reviewed by Cursor Bugbot for commit 2195d5d. 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 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 2195d5d. Configure here.}

[cursor]

Incorrect model mode set

High Severity

mode is set to unknown for meta-models/Muse-Glimmer-30B, a chat/agentic LLM with token pricing and a 128K context window. The same model on Together AI is chat. Gateways that key off mode will not treat this as a chat model.

 

^{Reviewed by Cursor Bugbot for commit 2195d5d. Configure here.}

[cursor]

Missing text input and output

High Severity

modalities lists only image input and omits text output. This model is a multimodal LLM that takes interleaved text and images and returns text. Clients that enforce modalities will reject normal prompts and treat it as image-only.

 

^{Reviewed by Cursor Bugbot for commit 2195d5d. Configure here.}