FlowTruxFlowTrux/Docs

AI Providers

Configure AI provider API keys and available models for your organization

FlowTrux supports multiple AI providers that power Agent nodes in your workflows. API keys are configured at the organization level and assigned to specific workspaces.

Supported Providers

Anthropic (Claude)

ModelBest For
claude-opus-4-6Most capable, complex multi-step reasoning, 1M context
claude-sonnet-4-6Fast, high-quality, 1M context
claude-opus-4-5Advanced reasoning and analysis
claude-sonnet-4-5Balanced performance and speed
claude-opus-4Strong reasoning, previous generation
claude-sonnet-4Fast, reliable general-purpose tasks
claude-haiku-4-5Lightweight tasks, high throughput, lowest cost

OpenAI (GPT)

ModelBest For
gpt-5.4Most capable OpenAI model, 1M context
gpt-5.3Agentic coding (Codex)
gpt-5.2Advanced reasoning
gpt-5Strong general-purpose performance
gpt-5-miniCost-effective for simpler tasks
o4-miniReasoning-optimized, compact

Google (Gemini)

ModelBest For
gemini-2.5-proMost capable Gemini model
gemini-2.5-flashFast responses, good balance
gemini-2.0-flashLightweight, high-speed tasks

Setup

1. Add an API Key

  1. Navigate to Settings in the sidebar (requires OWNER role).
  2. Open the AI Providers tab.
  3. Click Add Provider.
  4. Select the provider (Anthropic, OpenAI, or Google).
  5. Give it a name (e.g., "Production Anthropic Key").
  6. Paste your API key.
  7. Click Save.

The key is encrypted before being stored in the database. After saving, the key value is never exposed in the UI -- only the masked preview is shown.

2. Assign to a Workspace

API keys are not automatically available in all workspaces. You must explicitly assign them:

  1. Go to Settings > Workspaces.
  2. Click Edit on the target workspace.
  3. Under AI Providers, select which provider keys this workspace can use.
  4. Click Save.

Only models from assigned providers will appear in the Agent node model dropdown within that workspace.

How It Works at Runtime

When a workflow executes an Agent node:

  1. The engine looks up the selected model to determine which provider is needed.
  2. It loads the corresponding API key from the workspace's allowed providers.
  3. The key is decrypted in memory for the API call and never written to logs.
  4. If no matching provider is configured for the workspace, execution fails with a clear error message.

There is no fallback to environment variables. All AI provider configuration is done through the UI.

Multiple Keys

You can add multiple keys for the same provider. This is useful for:

  • Separating environments (e.g., "Development" and "Production" keys)
  • Cost tracking by assigning different keys to different workspaces
  • Key rotation without downtime -- add the new key, reassign workspaces, then remove the old key

Plan Limits

Your organization's plan may limit the number of AI provider keys you can configure. Check Settings > Plan & Usage to see your current limits.