Try the models with patient data. No commitment.
Access the latest models through an OpenAI-compatible end point. Accept your BAA at signup, swap your endpoint and API key, then start building today.
// 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);# 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,
)1,000+ independent practices trust Medsender
Trusted by practices from 1 location to 250+
You can't test with patient data until you have already committed.
Both paths ask you to commit before you can run a single test with real data. The models you want to evaluate the most are ones you can't try.
Host the models yourself
GPUs, deployment, and ongoing maintenance before you've written a line of product code.
Use another vendor
Work through the provider’s signing process before sending patient data.
Covered inference,
without the commitment.
Medsender handles the provider agreements, so your
team can start building instead of waiting on legal.
Keep your OpenAI SDK
Use the official OpenAI SDKs for Python or Node. Swap the endpoint and the key, and nothing else in your application changes.
BAA coverage on every key
Every call is in scope. There is no retention setting to remember and no way to write an uncovered call. US-region processing, no prompt retention, signed BAA.
The latest models
New releases are added as they come out, so you are not stuck on whatever was current when you signed up.
GLM
Kimi
MiniMax
QwenPay only for what you use
Pay the standard published rate for whichever model you call, plus a 5% service fee. Prepay with credits that draw down as you use them.
View pricingFrom signup to your first request.
No approval, no sales call, no minimum.
Create your account
Takes less than a minute. No card required until you add credits.
Sign your BAA
Review and and sign it yourself in the self-serve console. No commitment.
Create your key
Add credits, generate a key
and make our first request.
Ready to start building?
Get the latest models with no minimum spend, no platform fee, and no charge for your BAA.
Create your account