What happens when no provider qualifies?

The request fails with a clear message instead of silently relaxing your floor. Loosen the floor, star a qualifying provider, or use a local model.

Do the floors apply to the API too?

Yes. The same enforcement runs for chat, agents, and the OpenAI, Anthropic, and OpenRouter-compatible APIs: one floor, everywhere.

Where do the labels come from?

From providers' published policies, curated and kept up to date. They are best-effort labels, not guarantees, and each provider name links to its policy so you can verify for compliance needs.

Control which providers see your data

Different AI providers treat your prompts differently: some keep nothing, some retain them briefly, one or two may train on them. idapt labels every provider and lets you restrict routing to the ones that meet your bar 🛡️

Read the labels

Provider data policies show up throughout the product, so you can check before you chat:

Model cards in the model catalog show a No-train badge when the model's best route qualifies.
Model detail pages list every provider serving the model; open a provider row to see whether it trains, how long it retains data, and a link to its published policy.
The provider directory and the privacy page show the full labeled table.

No-train means the provider doesn't use your data to train models, but may retain it briefly (often ~30 days) for abuse monitoring.

Turn on a privacy floor

Instead of checking labels model by model, set a floor once and let idapt enforce it on every request:

Open your workspace's AI Routing
Find the Data policies card
Turn on Only endpoints that don't train on my data

The floor applies to chat, agents, and the API alike. Providers whose policy can't be verified are excluded, never assumed safe. The eligibility preview under the toggles shows exactly which providers remain.

Floors only ever tighten: an agent can be stricter than its workspace, never looser. Models running on your own computer always qualify.

Block a specific provider

Don't want a particular provider handling your data at all? Block it in AI Routing preferences and idapt never routes to it, for any model.

You can also block a provider for a single model from the providers list on that model's details page.

Bring your own keys

Connect your own provider API keys in AI Routing and requests for that provider run under your own account and contract terms. Keys are encrypted before storage and only ever used server-side. For setup, the free-tier caps (3 connections and 100 cloud calls every 30 days), and the paid requirement for using your key as an image, speech, or transcription default, see Bring your own provider keys.

Because your own account's settings apply, BYOK routes count as "unverified" under a privacy floor. Turn the floor off for BYOK traffic, or rely on your own provider agreement.

Skip providers entirely

For maximum privacy, run open models on your own computer, where no third-party AI provider is involved at all. See Run models locally.

FAQs

Your data and privacy

What idapt stores, who can see it, how AI providers handle it, and the controls that keep you in charge.

Bring your own provider keys

Connect your own OpenAI, Anthropic, or Google key, and route your usage straight to that provider's bill.

Choosing models

Browse 200+ AI models, read their cost bands, set the speed dial, and pick the right model for each conversation.

Run models locally

Install open models on your own computer with Ollama and run them privately in idapt: free, with no rate limits.

Up next

Bring your own provider keys

Connect your own OpenAI, Anthropic, or Google key, and route your usage straight to that provider's bill.

Was this helpful?

Read the labels

Provider data policies show up throughout the product, so you can check before you chat:

Model cards in the model catalog show a No-train badge when the model's best route qualifies.
Model detail pages list every provider serving the model; open a provider row to see whether it trains, how long it retains data, and a link to its published policy.
The provider directory and the privacy page show the full labeled table.

No-train means the provider doesn't use your data to train models, but may retain it briefly (often ~30 days) for abuse monitoring.

Turn on a privacy floor

Instead of checking labels model by model, set a floor once and let idapt enforce it on every request:

Open your workspace's AI Routing
Find the Data policies card
Turn on Only endpoints that don't train on my data

Floors only ever tighten: an agent can be stricter than its workspace, never looser. Models running on your own computer always qualify.

Block a specific provider

Don't want a particular provider handling your data at all? Block it in AI Routing preferences and idapt never routes to it, for any model.

You can also block a provider for a single model from the providers list on that model's details page.

Bring your own keys

Because your own account's settings apply, BYOK routes count as "unverified" under a privacy floor. Turn the floor off for BYOK traffic, or rely on your own provider agreement.

Skip providers entirely

For maximum privacy, run open models on your own computer, where no third-party AI provider is involved at all. See Run models locally.

FAQs

Your data and privacy

What idapt stores, who can see it, how AI providers handle it, and the controls that keep you in charge.

Bring your own provider keys

Connect your own OpenAI, Anthropic, or Google key, and route your usage straight to that provider's bill.

Choosing models

Browse 200+ AI models, read their cost bands, set the speed dial, and pick the right model for each conversation.

Run models locally

Install open models on your own computer with Ollama and run them privately in idapt: free, with no rate limits.

Up next

Bring your own provider keys

Connect your own OpenAI, Anthropic, or Google key, and route your usage straight to that provider's bill.

Was this helpful?