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

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
- The Neon backend is generally available release - Sep 18, 2026
The Neon backend is generally available, and every branch is a full copy.
- Claimable Neon, @neon/tools, and more release - Sep 11, 2026
Claimable Neon is provisioned by agents and claimed by humans.
- Neon backend in Europe, new AI Gateway models, Neon in Grok Bot, and CLI updates release - Sep 04, 2026
Neon backend launched in AWS Europe (Frankfurt), with new AI Gateway models, Neon in Grok Bot, and CLI updates.
- Install Neon into your coding agent, new Neon backend guides, and MCP stalled-query checks release - Aug 28, 2026
Neon added CLI setup commands for coding agents and MCP checks for stalled queries.
- Faster Lakebase Search setup, Neon CLI updates, and a Neon MCP Claude connector release - Aug 21, 2026
Lakebase Search extensions can be installed directly; Neon also added CLI updates and an MCP Claude connector.
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