AI Providers

Fruxon doesn't resell inference. You connect your own provider accounts, your own API keys, and your spend goes directly to OpenAI / Anthropic / Google / etc. The platform handles the orchestration; the model bill is yours.

Supported providers

Each provider has its own configuration — most need an API key; some need additional fields (region, project ID).

Connecting a provider

1. Open the agent in Studio.
2. Open the Configuration Panel (left sidebar) and select AI Providers.
3. Find the provider, expand it.
4. Paste the API key (and any additional fields).
5. Click Test to validate.
6. Click Save.

A Configured badge appears once the key is saved and validated.

You can connect multiple providers simultaneously — that's the whole point. Different steps can use different providers without copying keys.

Using a provider in a step

1. Add or select an Agent Step on the canvas.
2. In the step's config panel, pick the provider from the dropdown.
3. Pick the model.
4. Set provider-specific knobs (temperature, max tokens, top-p, reasoning mode, etc.).

Different steps can use different providers. Different steps within the same agent can use different keys for the same provider — useful for billing isolation.

Per-agent vs per-organization

Provider keys are configured per agent. This is intentional:

• Each agent can use distinct keys (separate billing, blast radius).
• A dev agent and a prod agent can be wired to different accounts without copying.
• Sub-agents inherit nothing — each agent's keys are independent.

If you have many agents and want to share keys, the organization-level pattern is to use the same key in each agent's config. (Organization-shared key bindings are on the roadmap.)

Mixing models for cost and quality

The economical pattern is to mix models within a single agent:

• Use a fast, cheap model (Haiku, GPT-4o-mini, Gemini Flash) for routing, classification, and simple extraction.
• Use a strong model (Opus, GPT-4o, Gemini Pro) for the user-visible final answer.
• Use a reasoning model (o-series, Claude with extended thinking) only on the steps that genuinely benefit from it — they're slower and more expensive.

Cost & Budgets breaks down how these decisions show up in your bill.

Bring-your-own cloud (Bedrock)

For regulated or sovereign deployments where inference needs to stay inside an account you control:

• AWS Bedrock — run Claude, Nova, Llama, and other Bedrock-hosted models in your AWS account. Configure your region and credentials in the Bedrock provider; Fruxon orchestrates without proxying inference.

Security

• API keys are encrypted at rest.
• Keys are never logged or echoed in traces — only the placeholder reference is captured.
• Editable only by Admins; not viewable after save (write-only).
• Rotate by overwriting; revoke by deleting.

Security →

Provider data handling

Fruxon doesn't train any models on your data and doesn't proxy your prompts through third parties. Prompts and outputs flow directly between Fruxon's runtime and your chosen provider.

Provider data policies still apply for inference itself — confirm in your contract with the provider:

• OpenAI's enterprise default: not used for training.
• Anthropic's API default: not used for training.
• For zero-retention guarantees: most providers offer it on enterprise contracts; configure it in your provider account.

Troubleshooting connections

Troubleshooting →

Next steps

• Agent Studio — wire providers into steps
• Cost & Budgets — track spend per model
• Security — how keys and secrets are protected
• Tools & Skills — what the model can do