Vai al contenuto
AI.info

tools

Neon

Neon provides branchable serverless Postgres and backend services for applications and coding agents.

Neon

In inglese

Neon provides managed Postgres with separated compute and storage, autoscaling, scale-to-zero, instant provisioning, and database branching. Its backend services also include Object Storage, Functions, Managed Better Auth, and an AI Gateway.

Developers use Neon for application databases, preview environments, testing, agent-built applications, file storage, authentication, and model calls. Neon does not host frontends or static sites, and AI Gateway model usage and other services may incur usage charges.

Features

  • Provision serverless Postgres databases with autoscaling and scale-to-zero
  • Create isolated database branches for previews, tests, and agent sessions
  • Query databases through a PostgREST-compatible HTTP interface
  • Store files in S3-compatible Object Storage that branches with database data
  • Deploy long-running Node.js Functions beside Postgres
  • Use Managed Better Auth with branchable users, sessions, and organizations
  • Call models from multiple providers through the AI Gateway
  • Manage projects and database resources through an API and CLI

Use cases

  • Create isolated databases for pull-request preview environments
  • Run integration tests against disposable Postgres branches
  • Build applications with database, storage, functions, and authentication
  • Deploy agent-built backends with branchable infrastructure
  • Store uploads alongside the database while keeping branches isolated
  • Call AI models without managing separate provider credentials

Pros

    Cons

      Latest updates

      Capabilities

      • Command line — “full access via MCP, CLI, and SDK.” source
      • Choice of models — “An agent can switch models without provisioning a separate provider account and key each time” source
      • API — “You can call AI models directly from Neon:” source
      • Official SDKs — “full access via MCP, CLI, and SDK.” source
      • Runs models for you — “Models are served through Databricks Foundation Model APIs” source
      • Search over your data — “Search Vector, keyword, and hybrid search” source

      Get it

      Security

      • SOC 2 Type II — “Neon undergoes annual SOC 2 Type II audits performed by accredited independent third party auditors.” source
      • SOC 2 — “Neon undergoes annual SOC 2 Type II audits performed by accredited independent third party auditors.” source
      • ISO 27001 — “These certifications validate our commitment to global standards.” source
      • GDPR — “Neon follows the GDPR framework, ensuring user rights, data minimization, and lawful processing.” source
      • HIPAA — “Neon has achieved HIPAA compliance to support customers handling protected health information (PHI).” source

      Pricing

      Starting price
      $1.50/mo
      Prices checked
      2026-09-24

      Free

      Free

      • 100 projects
      • 100 CU-hrs monthly per project
      • 0.5 GB of storage per project
      • Sizes up to 2 CU (8 GB RAM)
      • Unlimited team members
      • 5 GB of Object Storage

      Launch

      • $0.106 per CU-hour
      • $0.35 per GB-month
      • $0.20 per GB-month
      • $0.002 per branch-hour
      • $1.50 per extra branch-month
      • $0.09/GB-month
      • $0.023 per GB-month
      • $0.10 per active capacity-hour
      • $0.025 per waiting capacity-hour
      • $0.60 per 1M invocations
      • $0.10/GB
      • 100 projects
      • Up to 16 CU (64 GB RAM)
      • 3-day metrics/logs in UI
      • Up to 1M MAUs
      • Billing Support
      • Usage-based

      Scale

      • $0.222 per CU-hour
      • $0.35 per GB-month
      • $0.20 per GB-month
      • $0.002 per branch-hour
      • $1.50 per extra branch-month
      • $0.09/GB-month
      • $0.023 per GB-month
      • $0.12 per active capacity-hour
      • $0.03 per waiting capacity-hour
      • $0.60 per 1M invocations
      • $0.10/GB
      • $0.01 per GB
      • 1,000+ projects
      • Up to 56 CU (224 GB RAM)
      • SLAs, HIPAA, private network
      • Up to 1M MAUs
      • 14 days metrics/logs in UI
      • Usage-based
      Official website