Getting started
Go from a new account to a running model or database. Sign up, add a payment method, and deploy from the console or your terminal.
Create an account#
- Go to nistro.ai/signup.
- Enter your name, email, company and a password of at least 8 characters, then select Sign up. Signing up accepts the Terms of Use and Privacy Policy.
- Open the verification email and follow its link to activate your account.
- Sign in with your email and password.
You can also sign up and sign in with Google or GitHub.
Add a payment method#
Try Nistro AI Postgres for free until December 2026. Add a payment method to start deploying:
- In the console, open Billing.
- On the Payment Method card, select Configure and add your payment details on the billing provider's page.
When the card shows Configured, you're ready to deploy. Plans and prices are on the pricing page.
Deploy#
Pick a product and follow its quick start:
- Nistro AI Inference: deploy a model from Hugging Face and call it with
curlor the OpenAI SDK. - Nistro AI Postgres: create a managed database and connect to it with
psql. - Nistro AI Compute: GPU capacity reserved for two or three years.
Want your deployments inside your own AWS, Google Cloud, Azure or Nebius account? Connect it first; see Cloud accounts.
Install the CLI#
Create and manage deployments from your terminal with the nistro CLI. Install it on macOS, Linux or Windows (Git Bash):
curl -fsSL https://raw.githubusercontent.com/nistroai/ctl/main/install.sh | shOpen a new terminal, then sign in with your email and password and list your databases.
Signed up with Google or GitHub? Set a password first with Forgot password.
nistro login
nistro postgres listSee Nistro AI CLI for every command.
Next steps#
- Invite your team and set their roles: Teams and roles.
- Stay on top of your deployments: Alerts and activity.
- Open Grafana dashboards for your database from its Metrics card: Postgres monitoring.
- Track spend on the Usage page: Usage and billing.
- Move to dedicated machines with the Scale plan: Inference plans and Postgres plans.