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.
Agent nodes work without your own key
You don't need to bring an API key to start using Agent nodes. Every plan includes a monthly allowance of AI credits: when no provider key is configured for the workspace, Agent nodes run on FlowTrux's platform keys and each call is charged against your plan's credits based on token usage. The monthly credit allowance depends on your plan - check Settings > Usage for your current balance.
Adding your own API key changes the economics: calls made with your key are billed directly by the provider (Anthropic, OpenAI, or Google) and do not consume FlowTrux credits - there is no credit cap on your own key.
Supported Providers
Anthropic (Claude)
| Model | Best For |
|---|---|
claude-opus-4-8 | Most capable Claude model, complex multi-step reasoning |
claude-opus-4-7 | Advanced reasoning and analysis |
claude-opus-4-6 | Strong reasoning, long documents |
claude-sonnet-4-6 | Fast, high-quality - great default |
claude-haiku-4-5 | Lightweight tasks, high throughput, lowest cost |
claude-sonnet-4-5 | Balanced performance and speed, previous generation |
claude-opus-4-5 | Advanced reasoning, previous generation |
OpenAI (GPT)
| Model | Best For |
|---|---|
gpt-5.5 | Most capable OpenAI model |
gpt-5.5-pro | Hardest reasoning tasks, highest quality |
gpt-5.4 | Strong general-purpose performance |
gpt-5.3 | Agentic coding (Codex) |
Google (Gemini)
| Model | Best For |
|---|---|
gemini-2.5-pro | Most capable Gemini model |
gemini-2.5-flash | Fast responses, good balance |
gemini-2.5-flash-lite | Lightweight, high-speed, lowest cost |
Setup
1. Add an API Key
- Navigate to Settings in the sidebar (requires OWNER or ADMIN role).
- Open the AI Providers tab.
- Click Add Provider.
- Select the provider (Anthropic, OpenAI, or Google).
- Give it a name (e.g., "Production Anthropic Key").
- Paste your API key.
- 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:
- Go to Settings > Workspaces.
- Click Edit on the target workspace.
- Under AI Providers, select which provider keys this workspace can use.
- Click Save.
How It Works at Runtime
When a workflow executes an Agent node:
- The engine looks up the selected model to determine which provider is needed.
- If your organization has a matching provider key assigned to the workspace, it is used - decrypted in memory for the API call, never written to logs, and no credits are charged.
- If there is no matching org key, the call falls back to the platform key and is charged against your plan's monthly AI credits.
- Execution fails with a clear error only when neither path is available - for example, when your plan's credits are exhausted for the month and no org key is configured. The error tells you exactly what to do: add your own API key or upgrade your plan.
All AI provider configuration is done through the UI - keys are never read from environment variables or files.
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 > Usage to see your current limits and credit balance.