HIPAA Inference
Use Claude, GPT, Gemini, and many more with HIPAA data
Sign one BAA with us. We hold the BAAs with the providers. Then call covered models through one API.
Your BAA with Concentrate
Provider BAAs we hold
How it works
01
Tell us what you call
Share the models, endpoints, and features your app uses. We confirm which routes are covered.
02
Sign the BAA
You sign one BAA with Concentrate. Our staff then turn on HIPAA mode for your organization.
03
Call the API
Pick a covered model, or set the model to “auto” and we pick one on a covered, zero data retention route. Test with synthetic data first.
Routing, data handling, and organization controls are on the HIPAA LLM Gateway page.
Pricing
- $499 a month
- Access to all of our BAAs.
- Inference
- Billed separately at provider rates, with no markup. See Model Fortress.
At $100,000 a month of usage
| Per month | Concentrate | Aptible |
|---|---|---|
| Inference at provider list rates | $100,000 | $100,000 |
| Token markup | $0 | $15,000 |
| Monthly plan | $499 | $200 |
| Total | $100,499 | $115,200 |
Assumes the same models, token mix, and features, before negotiated discounts. Aptible prices from its LLM Gateway page, October 27, 2026. See the full Aptible comparison.
Questions before you buy
- What does the $499 a month cover?
- Access to the BAAs: yours with Concentrate, and ours with the providers that serve covered routes. It does not include inference.
- How is inference billed?
- Separately, at provider rates, with no markup. You pay for the tokens you use. Rates for each covered route are in the covered models table and in Model Fortress.
- Is there an auto router?
- Yes. Set the model to “auto” and we pick the model for you, using only BAA-covered routes with zero data retention.
- Do I need a separate BAA with each provider?
- Not for covered routes through Concentrate. We hold those agreements. They do not extend to provider accounts you use outside Concentrate, and Bring Your Own Key is unavailable on a HIPAA organization.
- Which models and provider routes are covered?
- Coverage depends on the serving provider, endpoint, and enabled features. The current routes and their rates are in covered models and in the BAA-eligible filter in Model Fortress.
- What happens to prompts and responses?
- On a HIPAA organization, request-content logging is locked off, so prompt and response bodies are not stored. See data handling.
- Can I use search or caching?
- Web search depends on how it runs. On a HIPAA organization, Concentrate’s search runs Exa in its HIPAA mode, with zero data retention on Exa’s side. A model’s own search tool runs on the provider, so coverage depends on that provider. Confirm your search setup with us before sending PHI. Caching is supported.
- Can I sign up and start today?
- Not self-service. You sign the BAA with Concentrate first. Concentrate staff then turn on HIPAA mode for your organization.
- How does this compare with other gateways?
- Aptible costs more once provider list rates pass about $2,000 a month. Price, prompt storage, and notes on OpenRouter, Kong, and Bifrost are on the Aptible comparison page.
One BAA for every covered provider
$499 a month for access to all of our BAAs. Inference at provider rates, no markup.