LLM Inference Gateway

Ship AI features faster.

Access the latest open models for applications that handle patient data, without negotiating separate provider agreements. Sign your BAA, swap your endpoint and API key, and start building today.

View code example
OpenAI SDK · Node
// npm install openai
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://llm.medsender.com/v1',
  apiKey: process.env.MEDSENDER_LLM_API_KEY,
});

const completion = await client.chat.completions.create({
  model: 'fast',
  messages: [
    { role: 'system', content: 'You are a clinical intake assistant. Answer in one sentence.' },
    { role: 'user', content: 'Why would a primary care office send a referral to a cardiologist?' },
  ],
  max_tokens: 256,
});
console.log(completion.choices[0].message.content);
OpenAI SDK · Python
# pip install openai
import os
from openai import OpenAI

client = OpenAI(
  base_url="https://llm.medsender.com/v1",
  api_key=os.environ["MEDSENDER_LLM_API_KEY"],
)

completion = client.chat.completions.create(
  model="fast", messages=[{"role":"user", "content":"Hello"}],
  max_tokens=256,
)
HIPAA-compliantUS data residencySelf-serve BAASOC 2 Type IINo commitment required for BAA

1,000+ independent practices trust Medsender

Trusted by practices from 1 location to 250+

The Problem

Provider agreements shouldn’t delay your launch.

Before you can launch features that use patient data, your team has provider requirements to work through. Provider approvals and security reviews can add days or weeks before launch.

Work through provider terms

Work through provider terms, including contract negotiation where required.

Wait for BAA coverage

Work through the provider’s signing process before sending patient data.

Resolve data-handling questions

Get answers on processing locations, prompt retention, and training policies.

Verify coverage settings

Confirm which endpoints and request settings fall under the agreement.

Your launch is still waiting

Your patient-data features can’t go live until these requirements are resolved.

The Solution

Latest open models.
No provider negotiations.

Medsender handles the provider agreements and simplifies BAA coverage, so your team can focus on building.

Keep your OpenAI SDK

Use the official OpenAI SDKs for Python or Node with one API call.

BAA coverage on every key

Build features that handle patient data without negotiating a separate BAA with each model provider.

Latest open-source models

Access the latest open-source models as they’re released, at competitive prices.

Prepaid credits

Pay published model rates plus a 5% service fee. Prepay with credits that draw down as you use them.

Getting Started

From sign-up to your first request.

Get Developer Console access, accept the agreement, sign your BAA, and create your API key.

1

Get Developer Console access

Sign up with your work email and select LLM inference.

2

Accept the agreement

Review and accept the agreement through the self-serve console.

3

Sign your BAA

Review and sign your BAA online.

4

Create your API key

Create a key in the console, add credits, and make your first request.

Ready to start building?

Get access to the latest open models for your healthcare application. No minimum spend, and no charge for your BAA.

Get Developer Console access
FAQs

Frequently asked questions about LLM Inference Gateway

Only if the provider has signed a BAA with you and the call is configured to fall under it. Most model APIs are not covered by default, and some require zero data retention to be set per request, so a signed agreement alone does not mean your calls are in scope. Once you’ve signed your BAA, requests through the Medsender endpoint are covered without separate per-request coverage settings.
Set the Medsender base URL and API key in the official OpenAI SDK for Python or Node. You can keep your existing SDK client, but should check that your chosen model supports the parameters and features your application uses.
Current open-source models, with new open-weight releases added as they come out.
Yes. After getting Developer Console access, you can review and sign your BAA through the self-serve process.
There is no minimum spend or sales conversation required. Get Developer Console access, accept the agreement, and sign your BAA through the self-serve process.
You pay the standard published rate for whichever model you call, plus a 5% service fee. That’s the whole bill: no subscription, no minimum, and no charge for the BAA. You prepay with credits, and usage draws the balance down.