---
name: lingtai-ai/preset-skill-nvidia
source: https://app.decimal.ai/s/lingtai-ai-preset-skill-nvidia@3/SKILL.md
source_sha256: 5ba8c2936783
---

# `nvidia`

`nvidiaPreset()` in `tui/internal/preset/preset.go` ships exact
model `meta/llama-3.3-70b-instruct` at `https://integrate.api.nvidia.com/v1`
with OpenAI compatibility and `NVIDIA_API_KEY`. This default model is
text-only and the manifest has no `vision` capability.

## Template-specific settings

The same hosted gateway may offer other VLM slugs, but a clone selecting one
still needs an explicit `capabilities.vision` entry; changing only `llm.model`
does not wire a LingTai vision route. Read the official [NVIDIA API Catalog](https://build.nvidia.com/),
[model catalog](https://build.nvidia.com/models), and [NIM API reference](https://docs.api.nvidia.com/nim/reference/llm-apis)
on demand. No NVIDIA plan-level vision MCP is established. Do not switch
providers or auto-load/invoke an MCP. Recheck TUI source for the template
fields after changes. Never guess a key or copy the volatile catalog into this
manual.

## Operations

For base URL/API-compat/model/capability declaration shape versus
credentials, see `reference/operations/endpoint-capabilities/SKILL.md`.