Pricing

Access medical-grade reasoning through one simple, compliant API

Transcribe, extract, and reason over clinical conversations and data — ship clinical-grade AI applications on compliant, scalable infrastructure.

Growth
For startups and teams shipping healthcare AI
Start building with $50 in free credits
Audio input
$40 / 1M tokens
Text input
$5 / 1M tokens
Text ouptut
$20 / 1M tokens
Audio output
Coming soon
Prepaid credits. No billing surprises.
Enterprise
For orgs with custom scale, performance or compliance requirements
Custom rate limits
Alerts and audit logs
Model fine-tuning
Self-hosted deployment

Growth

Access Corti's AI infrastructure with flexible, pay-as-you-go pricing. No setup fees, no contracts, and usage that scales with your needs.

Audio input

$40 / 1M tokens

Text Input

$5 / 1M tokens

Text Output

$20 / 1M tokens

Audio Output

Coming soon

Enterprise

Design a custom AI infrastructure plan for teams with unique security, compliance, or scale requirements.

Custom rate limits

Model fine tuning

Alerts & audit logs

Self-hosted deployment

“By combining Dedalus’ workflow expertise with Corti’s real-time reasoning engine, we’re delivering exactly what clinicians have been asking for — smarter tools that save time and improve care.”
Jan Rusch
Director Integrated Technologies at Dedalus

Ship compliant AI built for healthcare on the Corti API

Built for healthcare

Trained on clinical data

Native medical workflow comprehension

Real-time performance

Edge-optimized medical models

Real-time clinical reasoning

Smooth dev experience

Complete API and SDK docs

Quickstart code examples

OpenAPI spec

Built-in compliance & data governance

HIPAA-ready with templated BAA

ISAE 3000 Certification

Audit-ready transparency

FAQs

Explore on your own or talk to us if you need a hand. If you're not sure where to begin, or want to make a plan together, book a scoping call.

Can I sign up for free?

Yes! You can explore Corti’s API for free with a limited trial — no upfront commitment required.

We believe in delivering value from the start. That’s why we offer $50 in free credits to help you test and integrate our API into your application at no initial cost.

How does billing work?

For Growth customers, purchase credit upfront with a credit card. Credit will be deducted from your balance as you make calls to our API.

For Enterprise customers, we offer flexible credit purchases, invoicing, and custom terms. Speak with our team to craft a plan that fits your needs.

What is a token?

A token is a chunk of text (usually a piece of a word) that our models use to process your input. Think of it like the building blocks of a sentence.

  • 1 token ≈ 4 characters of English
  • 100 tokens ≈ 75 words

Our pricing is based on how many tokens your request uses, including both input and output. Different languages and model types may tokenize text differently, but we handle all of that automatically.

Do you have different pricing for different models?

We keep it simple. We apply a unified base token rate across all API endpoints, regardless of which endpoints you’re accessing. Your credits can be spent flexibly across your use cases, allowing you to build without worrying about feature gating or pricing tiers.

What is your standard rate limit?

Our standard rate limit is 10 concurrent streams per organization. Enterprise plans can request higher limits based on their needs.

Ship in minutes on Corti API

Access Corti’s AI infrastructure with flexible, pay-as-you-go pricing. No setup fees, no contracts, and usage that scales with your needs.