feat(deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning.

---

Note

Low Risk
Metadata-only addition with no runtime or auth changes; incomplete YAML vs other models could affect discovery or routing if validators require extra fields.

Overview
Adds a new DeepInfra provider YAML for nvidia/NVIDIA-Nemotron-3.5-Lightning (auto-generated by model-addition-agent).

The entry defines per-token costs ($0.05/M input, $0.20/M output), a 28,672 context and max output limit, and mode: unknown. It is thinner than sibling Nemotron files (no status, provisioning, sources, modalities, or supportedModes), which may matter if downstream tooling expects those fields.

^{Reviewed by Cursor Bugbot for commit c75e20e. 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 c75e20e. Configure here.}

[cursor]

Wrong mode for chat model

Medium Severity

mode is set to unknown for nvidia/NVIDIA-Nemotron-3.5-Lightning, but this is an OpenAI-compatible chat model with tool calling and reasoning. Consumers that filter on mode: chat will omit it, so it will not appear or route as a chat model.

 

^{Reviewed by Cursor Bugbot for commit c75e20e. Configure here.}