HelixML

Configure LLM providers

Connect Anthropic, OpenAI, Google, Groq, AWS Bedrock, NVIDIA NIM, Ollama, LM Studio, and other providers to Helix so agents have inference available.

Helix doesn't bundle its own models — it routes to providers you configure. Providers can be set at three levels:

  • User — personal providers, visible only to you (Account → AI Providers)
  • Organisation — shared across all org members (Organisation → Providers); see Manage your organisation
  • Installation — configured in Helm values for self-hosted deployments; available to all users on the instance

This guide covers UI configuration and Helm values. For org-level providers, see Manage your organisation: Configure org-level AI providers.

Adding a provider in the UI

Go to Account → AI Providers and click Add Provider. Select the provider type, paste your API key, and save.

Supported providers

ProviderNotes
AnthropicClaude models (Sonnet, Opus, Haiku). Recommended for coding agents.
OpenAIGPT-4o, o1, o3, and other OpenAI models
Google GeminiGemini models via the Gemini API
NVIDIA NIMGPU-accelerated inference; add the NIM base URL and API key
AWS BedrockClaude and other models via Amazon Bedrock; configure region and AWS credentials
GroqUltra-low latency open-source model inference (Llama, Mistral, Gemma)
CerebrasWafer-scale inference for fast open-source models
xAI GrokGrok models from xAI
Together AIWide catalogue of hosted open-source models
Fireworks AIFast inference for open-source models
OllamaLocal model server; run models on your own hardware
LM StudioLocal model server with on-demand model loading; run models on your own hardware
Custom (OpenAI-compatible)Any endpoint that speaks the OpenAI /v1/chat/completions API — vLLM, LocalAI, etc.

Once a provider is added, its models become available in the Model dropdown on any project, agent app, or agent.

Choosing a model for a coding project

Set model and provider on the agent in your project YAML:

spec:
  agent:
    name: "My Agent"
    runtime: claude_code
    model: claude-sonnet-4-6
    provider: anthropic

Claude Code is an exception — it manages its own model selection. Set runtime: claude_code and omit model/provider.

Helix Cloud: built-in providers

On Helix Cloud, built-in Helix inference providers are available by default — you can use these without adding your own API keys. Add your own keys if you want to use a specific model tier or route to your own accounts.

Self-hosted: configure providers via Helm

For Kubernetes deployments, configure providers under controlplane.providers in your values.yaml. Use existingSecret to keep API keys out of your values file and git history:

kubectl create secret generic anthropic-api-key \
  --from-literal=api-key="sk-ant-..."
controlplane:
  providers:
    anthropic:
      existingSecret: "anthropic-api-key"
      existingSecretApiKeyKey: "api-key"
    openai:
      existingSecret: "openai-api-key"
      existingSecretApiKeyKey: "api-key"
    groq:
      existingSecret: "groq-api-key"
      existingSecretApiKeyKey: "api-key"
    vllm:
      baseUrl: "http://my-vllm.vllm.svc.cluster.local:8000/v1"

See Linux & Kubernetes for the full Helm values reference.

Local models with Ollama (Mac App)

On the Mac App with 64 GB+ unified memory, run models locally via Ollama:

  1. Install Ollama
  2. Pull a model: ollama pull llama3.3
  3. In Helix, add an Ollama or Custom (OpenAI-compatible) provider with base URL http://localhost:11434/v1 and no API key
  4. The model appears in the model dropdown as llama3.3

Toggle wifi off and the agent still works — entirely local.

Local models with LM Studio (Mac App)

LM Studio exposes an OpenAI-compatible server, so you can serve local models to Helix the same way you would with Ollama:

  1. Install and open LM Studio and download a model.
  2. LM Studio's local server runs automatically on port 1234 — no extra configuration needed.
  3. In Helix, add an LM Studio provider. The base URL defaults to the local LM Studio server (http://host.docker.internal:1234/v1) and no API key is required.
  4. Loaded models appear in the Model dropdown.

Like Ollama, LM Studio loads models on demand: the first chat completion that targets a model which isn't loaded prompts LM Studio to load it automatically, so you don't need to pre-load a model before using it. (Expect the first request to a cold model to take a few extra seconds while it loads.)

On the Mac App, Helix can also auto-detect a locally-running LM Studio or Ollama server that isn't connected yet and offer a one-click Connect to add it as a provider. Connected local servers can be managed — including loading and unloading individual models — from the provider's detail page.

AWS Bedrock

Bedrock uses AWS IAM credentials rather than an API key:

  1. Add an AWS Bedrock provider and choose your region.
  2. Provide an IAM access key and secret (or use an instance role for EC2/EKS deployments).
  3. Enable the models you want in the AWS Bedrock console — models must be explicitly enabled per region.

For Helm-based deployments:

controlplane:
  providers:
    bedrock:
      region: "us-east-1"
      existingSecret: "aws-credentials"
      existingSecretAccessKeyKey: "access-key-id"
      existingSecretSecretKeyKey: "secret-access-key"

Anthropic via GCP Vertex AI

For organisations that prefer to route Anthropic inference through Google Cloud:

controlplane:
  providers:
    anthropic:
      vertexProjectID: "my-gcp-project"
      vertexRegion: "us-east5"
      vertexCredentialsSecret: "gcp-vertex-credentials"

See the chart's values-example.yaml for the full shape.

Model availability

The Reference: Supported models page lists model identifiers and which providers support them.