Choose an Inference Provider

Choose a provider based on where the model runs, which API it exposes, and which credential you can supply. NemoClaw validates the provider and model before it creates the sandbox.

On native N1x FASTOS, accept the Deferred managed-vLLM preview or enter standard onboarding by declining Express. You can also enter standard onboarding by setting NEMOCLAW_NO_EXPRESS=1 without a provider, or by setting a recognized NEMOCLAW_PROVIDER value other than Local NVIDIA NIM or install-vllm. Set NEMOCLAW_PROVIDER=install-vllm only to bypass the prompt with the same Deferred managed-vLLM preview intent. N1x remains Deferred, each standard provider keeps its existing requirements, and local NVIDIA NIM remains unavailable. On a qualifying Windows WSL N1x host, Windows Express and non-interactive onboarding automatically select managed llama.cpp when no provider is requested or recorded and NEMOCLAW_MODEL is unset. Windows Express acceptance or the required non-interactive third-party software acceptance is the opt-in for this Experimental path. With NEMOCLAW_LLAMACPP_RECIPE unset, onboarding selects Qwen 3.6; a compatible explicit recipe selects that managed recipe. Ordinary interactive onboarding can select another listed provider. Other Windows WSL Express installs use WSL-local Ollama. Windows-host Ollama remains available through manual onboarding when Docker Desktop WSL integration is enabled, DOCKER_HOST is unset, Docker uses the local default context, and Ollama has a loopback-only listener that is reachable from Docker and rejects unrecognized HTTP Host headers.

Provider Support

Use this status table to distinguish validated provider integrations from adapters whose behavior depends on the selected compatible implementation.

Provider	Status	Endpoint type	Notes
NVIDIA Endpoints	Tested	OpenAI-compatible	Hosted models on integrate.api.nvidia.com
OpenRouter	Tested	OpenAI-compatible	First-class onboarding route for OpenClaw, Hermes, and LangChain Deep Agents Code. NemoClaw registers the `openrouter-api` provider through OpenShell’s `openai` profile with a host runtime adapter URL; host-side validation and runtime traffic send the default OpenRouter attribution headers.
OpenAI	Tested	Native OpenAI-compatible	Uses OpenAI model IDs
Other OpenAI-compatible endpoint	Tested with limitations	Custom OpenAI-compatible	Custom base-URL adapter for servers that implement OpenAI-compatible `/v1/chat/completions` or `/v1/responses`. Behavior on OpenAI-compatible proxies, gateways, and self-hosted implementations may vary; this row claims the adapter, not the universe of compatible endpoints.
Anthropic	Tested	Native Anthropic	Uses anthropic-messages
Other Anthropic-compatible endpoint	Tested with limitations	Custom Anthropic-compatible	Adapter path validated with AWS Bedrock (`src/lib/onboard/bedrock-runtime.ts`). Behavior on other Anthropic-compatible proxies and gateways may vary; this row claims the adapter, not the universe of compatible endpoints.
Google Gemini	Tested	OpenAI-compatible	Uses Google’s OpenAI-compatible endpoint
Hermes Provider	Hermes only	OpenAI-compatible route	Available when onboarding Hermes Agent through `nemohermes`
Local Ollama	Tested with limitations	Local Ollama API	Available when Ollama is installed or running on the host. Validated default models: `qwen3.6:35b` (high VRAM), `nemotron-3-nano:30b` (medium VRAM), `qwen3.5:9b` (low VRAM fallback).
Local llama.cpp (already running)	Experimental	Local OpenAI-compatible	Attaches only to an authenticated operator-managed server on loopback port `8081` that passes cooperative native llama.cpp fingerprinting. NemoClaw does not own its server, model, or lifecycle.
Local llama.cpp (managed)	Experimental	Local OpenAI-compatible	Uses repository-owned YAML recipes and exact GGUF verification. The selected runtime-provider boundary owns lifecycle; all currently qualified profiles require Docker. Qualified DGX Spark hosts offer NVIDIA Nemotron 3 Nano 30B-A3B. Qualifying Windows WSL N1x hosts automatically use managed llama.cpp during Windows Express or non-interactive onboarding when no provider is requested or recorded and `NEMOCLAW_MODEL` is unset. An unset recipe selects Qwen 3.6 35B-A3B; a compatible explicit recipe selects that managed recipe. The N1x recipe remains pending physical agent qualification.
Local NVIDIA NIM	Experimental	Local OpenAI-compatible	Requires `NEMOCLAW_EXPERIMENTAL=1` and a NIM-capable NVIDIA GPU. Host must have the NVIDIA Container Toolkit installed and a healthy CDI spec. Onboarding evaluates the canonical `host.gpu.nvidia_available`, `host.gpu.container_toolkit_available`, and `host.gpu.cdi_healthy` readiness capabilities before gateway, image, or sandbox lifecycle effects. NIM images pull from `nvcr.io` and require NGC registry login. NemoClaw gates this path behind the experimental flag. Onboarding filters the validated image list by usable memory. In non-interactive mode, onboarding selects the first compatible model unless the operator sets `NEMOCLAW_MODEL`. Model selection uses detected free GPU memory. If free memory is unavailable, NemoClaw uses total GPU memory. On DGX Spark, NemoClaw caps usable memory at 50 percent of total memory to match NIM’s reported unified-memory limit. The Nemotron 3 Super catalog minimum includes NIM’s reported runtime allocation. Local NVIDIA NIM is unavailable on N1x. NemoClaw omits the provider from onboarding and rejects `NEMOCLAW_PROVIDER=nim-local` on N1x. Select another standard provider or use the Deferred managed-vLLM preview on N1x. On Linux arm64 DGX Spark and DGX Station hosts, onboarding warns that some NIM images may not publish a `linux/arm64` manifest; the warning is advisory, and the selected image pull can still fail when the registry has no matching platform manifest. Managed vLLM has host-specific default models and is not gated on the same boxes. Validated images referenced in `src/lib/inference/config.ts` and `nemoclaw/src/index.ts`: `nvidia/nemotron-3-super-120b-a12b` (default cloud model), `nvidia/nemotron-3-nano-30b-a3b`, `nvidia/llama-3.3-nemotron-super-49b-v1.5`.
Local vLLM (already running)	Tested with limitations	Local OpenAI-compatible	On a qualified N1x host, this route requires explicit standard-onboarding intent and remains unvalidated. On other hosts, no explicit intent is required. It appears in the onboarding menu when NemoClaw detects a server on `localhost:${NEMOCLAW_VLLM_PORT:-8000}`. The model is whatever the existing server serves.
Local vLLM (managed install/start)	Tested with limitations	Local OpenAI-compatible	Managed install/start requires Docker on `PATH`; attaching an already-running local vLLM server is a separate path. Appears by default on DGX Spark and qualifying DGX Station GB300 hosts. A labeled Deferred preview appears on hosts that match the N1x identity requirements; N1x remains Deferred until a physical NemoClaw Express E2E test passes. DGX Station is Tested with limitations across qualified profiles on one physical DGX Station GB300. Full Station Express end-to-end qualification for the accepted no-OTA DGX OS `7.6.x` profile is pending. Dual-Station configurations are not yet validated, and dedicated CI coverage is not available. For canonical Station qualification and host preparation, see the Additional Setup page for OpenClaw, Hermes, or Deep Agents. Generic Linux NVIDIA GPU hosts require `NEMOCLAW_EXPERIMENTAL=1` or `NEMOCLAW_PROVIDER=install-vllm`, NVIDIA Container Toolkit, and CDI. NemoClaw pins runtime images to immutable digests. Station Express defaults to `nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4`; `--station-deepseek` selects `deepseek-ai/DeepSeek-V4-Flash`. Direct managed-vLLM defaults are `nvidia/Qwen3.6-35B-A3B-NVFP4` on DGX Spark and the Deferred N1x preview, `deepseek-ai/DeepSeek-V4-Flash` on DGX Station, and `nvidia/NVIDIA-Nemotron-3-Nano-4B-FP8` on generic Linux NVIDIA GPU hosts. Image pulls from `nvcr.io` require NGC registry login.

Hosted Providers

Hosted providers use provider-managed endpoints and curated model choices.

Provider	API route	Credential	Setup guide
NVIDIA Endpoints	OpenAI-compatible Chat Completions	`NVIDIA_INFERENCE_API_KEY`	Use NVIDIA Endpoints
OpenRouter	OpenAI-compatible Chat Completions	`OPENROUTER_API_KEY`	Use OpenRouter
OpenAI	Native OpenAI-compatible	`OPENAI_API_KEY`	Use OpenAI
Anthropic	Anthropic Messages	`ANTHROPIC_API_KEY`	Use Anthropic
Google Gemini	Google OpenAI-compatible Chat Completions	`GEMINI_API_KEY`	Use Google Gemini

Local Providers

Local providers run on the host and keep inference traffic on infrastructure that you manage.

Provider	When it appears	Setup guide
Local Ollama	Ollama is installed or running on the host.	Use Ollama
Local vLLM already running	NemoClaw detects a server on `localhost:${NEMOCLAW_VLLM_PORT:-8000}`. Native N1x requires explicit standard-onboarding intent.	Set Up vLLM
Local vLLM managed install	Docker is available on `PATH`, the host matches a supported GPU profile, and any required opt-in is present. Attaching an already-running local vLLM server is separate.	Set Up vLLM
Local llama.cpp already running	You explicitly select an authenticated server on loopback port `8081`.	Set Up llama.cpp
Local llama.cpp managed install	A qualified DGX Spark or Windows WSL N1x host satisfies the declarative recipe requirements.	Set Up llama.cpp
Local NVIDIA NIM	Unavailable on native N1x FASTOS. On other hosts, a NIM-capable NVIDIA GPU must be present and experimental setup must be enabled.	Set Up NVIDIA NIM

Compatible Endpoints

Use a compatible endpoint when you operate a server or gateway that implements a supported inference API.

Provider option	Required API	Credential	Setup guide
Other OpenAI-compatible endpoint	`/v1/chat/completions`, with optional `/v1/responses` selection	`COMPATIBLE_API_KEY`	Set Up an OpenAI-Compatible Endpoint
Other Anthropic-compatible endpoint	`/v1/messages` for supported agents or `/v1/chat/completions` for OpenAI-compatible-only agents	`COMPATIBLE_ANTHROPIC_API_KEY`	Set Up an Anthropic-Compatible Endpoint

Behavior can vary across compatible proxies, gateways, and self-hosted implementations. The documented support applies to the NemoClaw adapter rather than every compatible endpoint implementation.

Routed Inference

Use Model Router when you want a host-side router to select from a configured model pool. The router registers as an OpenAI-compatible provider while the sandbox remains on inference.local.

Next Step

After you select a provider class, Choose a Model to compare curated hosted models by task fit.