NVIDIA · OpenClaw (original) (raw)

Providers

NVIDIA provides an OpenAI-compatible API at https://integrate.api.nvidia.com/v1 for open models for free. Authenticate with an API key frombuild.nvidia.com. OpenClaw defaults the NVIDIA provider to Nemotron 3 Ultra, NVIDIA's 550B total / 55B active reasoning model for long-context agentic work.

Getting started

• Get your API key

Create an API key at build.nvidia.com.

• Export the key and run onboarding

bash

export NVIDIA_API_KEY="nvapi-..."openclaw onboard --auth-choice nvidia-api-key  

• Set an NVIDIA model

bash

openclaw models set nvidia/nvidia/nemotron-3-ultra-550b-a55b  

For non-interactive setup, you can also pass the key directly:

bash

openclaw onboard --auth-choice nvidia-api-key --nvidia-api-key "nvapi-..."

Config example

json5

{  env: { NVIDIA_API_KEY: "nvapi-..." },  models: {    providers: {      nvidia: {        baseUrl: "https://integrate.api.nvidia.com/v1",        api: "openai-completions",      },    },  },  agents: {    defaults: {      model: { primary: "nvidia/nvidia/nemotron-3-ultra-550b-a55b" },    },  },}

Featured catalog

When an NVIDIA API key is configured, OpenClaw setup and model-selection paths try NVIDIA's public featured-model catalog fromhttps://assets.ngc.nvidia.com/products/api-catalog/featured-models.json and caches the ranked result for 24 hours. New featured models from build.nvidia.com therefore appear in setup and model-selection surfaces without waiting for an OpenClaw release. When the live feed is available, the first returned model is the default option shown during NVIDIA setup.

The fetch uses a fixed HTTPS host policy for assets.ngc.nvidia.com. If no NVIDIA API key is configured, or if that public catalog is unavailable or malformed, OpenClaw falls back to the bundled catalog and bundled default below.

Nemotron 3 Ultra

Nemotron 3 Ultra is the default NVIDIA model in OpenClaw. NVIDIA's build page fornvidia/nemotron-3-ultra-550b-a55blists it as an available free endpoint with a 1M-token context specification. The bundled catalog records a 16,384-token max output to match NVIDIA's current OpenAI-compatible sample request for the hosted endpoint.

Use Ultra for the highest-capability NVIDIA default. Keep Super selected when you want the smaller Nemotron 3 option, or choose one of the third-party models hosted in NVIDIA's catalog when their context, latency, or behavior fits better. The bundled Ultra row sends chat_template_kwargs.enable_thinking: false andforce_nonempty_content: true by default so normal chat output stays in the visible answer instead of exposing reasoning text.

Bundled fallback catalog

Advanced configuration

Auto-enable behavior

The provider auto-enables when the NVIDIA_API_KEY environment variable is set. No explicit provider config is required beyond the key.

Catalog and pricing

OpenClaw prefers NVIDIA's public featured-model catalog when NVIDIA auth is configured and caches it for 24 hours. The bundled fallback catalog is static and keeps deprecated shipped refs for upgrade compatibility. Costs default to 0 in source since NVIDIA currently offers free API access for the listed models.

OpenAI-compatible endpoint

NVIDIA uses the standard /v1 completions endpoint. Any OpenAI-compatible tooling should work out of the box with the NVIDIA base URL.

Nemotron 3 Ultra reasoning params

NVIDIA's Ultra sample request uses chat_template_kwargs.enable_thinkingand reasoning_budget for reasoning output. OpenClaw's bundled Ultra row disables template thinking by default for normal chat use. If you need to opt into NVIDIA reasoning output or force other NVIDIA-specific request fields, set per-model params and keep provider-specific overrides scoped to the NVIDIA model:

json5

{  agents: {    defaults: {      models: {        "nvidia/nvidia/nemotron-3-ultra-550b-a55b": {          params: {            chat_template_kwargs: { enable_thinking: true },            extra_body: { reasoning_budget: 16384 },          },        },      },    },  },}

params.extra_body is the final OpenAI-compatible request-body override, so use it only for fields NVIDIA documents for the selected endpoint.

Slow custom provider responses

Some NVIDIA-hosted custom models can take longer than the default model idle watchdog before they emit a first response chunk. For custom NVIDIA provider entries, raise the provider timeout instead of raising the whole agent runtime timeout:

json5

{  models: {    providers: {      "custom-integrate-api-nvidia-com": {        baseUrl: "https://integrate.api.nvidia.com/v1",        api: "openai-completions",        apiKey: "NVIDIA_API_KEY",        timeoutSeconds: 300,      },    },  },  agents: {    defaults: {      models: {        "custom-integrate-api-nvidia-com/meta/llama-3.1-70b-instruct": {          params: { thinking: "off" },        },      },    },  },}

Was this useful?

Edit sourceRaise issue

PreviousNovitaAINextOllama

On this page

On this page

Getting startedConfig exampleFeatured catalogNemotron 3 UltraBundled fallback catalogAdvanced configurationRelated