Files
bot/docs/providers/nvidia.md
zeekay 4bdc9ee3e4 chore: rebrand openclaw → hanzo-bot for bridge merge
Comprehensive rename of all openclaw references to hanzo-bot equivalents:
- Package: openclaw → @hanzo/bot
- Binary: openclaw → hanzo-bot
- Types: OpenClaw* → Bot*
- Env vars: OPENCLAW_* → BOT_*
- Android: ai.openclaw.android → ai.hanzo.bot.android
- iOS/macOS: ai.openclaw.* → ai.hanzo.*
- Swift modules: OpenClaw* → Bot*
- Plugins: openclaw.plugin.json → bot.plugin.json
- Paths: .openclaw/ → .hanzo/bot/
- URLs: github.com/openclaw → github.com/hanzoai
2026-02-26 22:36:01 -08:00

1.4 KiB

summary, read_when, title
summary read_when title
Use NVIDIA's OpenAI-compatible API in Bot
You want to use NVIDIA models in Bot
You need NVIDIA_API_KEY setup
NVIDIA

NVIDIA

NVIDIA provides an OpenAI-compatible API at https://integrate.api.nvidia.com/v1 for Nemotron and NeMo models. Authenticate with an API key from NVIDIA NGC.

CLI setup

Export the key once, then run onboarding and set an NVIDIA model:

export NVIDIA_API_KEY="nvapi-..."
bot onboard --auth-choice skip
bot models set nvidia/nvidia/llama-3.1-nemotron-70b-instruct

If you still pass --token, remember it lands in shell history and ps output; prefer the env var when possible.

Config snippet

{
  env: { NVIDIA_API_KEY: "nvapi-..." },
  models: {
    providers: {
      nvidia: {
        baseUrl: "https://integrate.api.nvidia.com/v1",
        api: "openai-completions",
      },
    },
  },
  agents: {
    defaults: {
      model: { primary: "nvidia/nvidia/llama-3.1-nemotron-70b-instruct" },
    },
  },
}

Model IDs

  • nvidia/llama-3.1-nemotron-70b-instruct (default)
  • meta/llama-3.3-70b-instruct
  • nvidia/mistral-nemo-minitron-8b-8k-instruct

Notes

  • OpenAI-compatible /v1 endpoint; use an API key from NVIDIA NGC.
  • Provider auto-enables when NVIDIA_API_KEY is set; uses static defaults (131,072-token context window, 4,096 max tokens).