> Full Neon documentation index: https://neon.com/docs/llms.txt
# Gemini 4 Argon, Apple and Microsoft sign-in, HIPAA for backend services, new Functions templates, and more
## Gemini 4 Argon is now available on the AI Gateway
The AI Gateway now serves Google's [Gemini 4 Argon](https://neon.com/docs/ai-gateway/models/gemini-4-argon), with a 1M-token context window and text, image, video, audio, and PDF input. Call it through the chat completions or native Gemini endpoint, or with the AI SDK:
```typescript
import { neon } from '@neon/ai-sdk-provider';
import { generateText } from 'ai';
const { text } = await generateText({
model: neon('gemini-4-argon'),
prompt: 'Explain database branching in one sentence.',
});
console.log(text);
```
To use the native Gemini endpoint, see [Gemini API](https://neon.com/docs/ai-gateway/gemini).
## Managed Better Auth adds Apple and Microsoft sign-in
[Managed Better Auth](https://neon.com/docs/auth/overview) now supports Apple and Microsoft Entra ID as OAuth providers, alongside Google, GitHub, and Vercel. Add either one from your project's **Better Auth** settings, the Neon CLI, or the Neon API, using your own Apple or Entra app credentials. See [Set up OAuth](https://neon.com/docs/auth/guides/setup-oauth).
## Tune Lakebase Search indexes
Version 1.1.2 of the [`lakebase_vector`](https://neon.com/docs/extensions/lakebase-vector) extension, part of [Lakebase Search](https://neon.com/docs/ai/lakebase-search), is now available on Postgres 16, 17, and 18. This release adds functions that recommend `lakebase_ann.probes` settings for your index, so you can trade off recall and latency without trial and error:
- `lakebase_ann_advise` recommends `probes` values with estimated recall and measured query latency.
- `lakebase_ann_tune` recommends `probes` values with estimated recall only.
- `lakebase_ann_latency` measures average, p50, and p95 query latency for the `probes` values you supply.
- `lakebase_ann_sample` samples rows from the indexed table to use as tuning queries when you don't have real ones.
```sql
SELECT probes, recall, avg_ms, p50_ms, p95_ms
FROM lakebase_ann_advise(
'items_embedding_idx'::regclass,
ARRAY(
SELECT embedding FROM lakebase_ann_sample(NULL::items, 512)
WHERE embedding IS NOT NULL
)
);
```
If you already have the `lakebase_vector` extension installed, run `ALTER EXTENSION lakebase_vector UPDATE` to get the new functions. See [Get recommended probes values](https://neon.com/docs/extensions/lakebase-vector#get-recommended-probes-values) and [Upgrade the extension and indexes](https://neon.com/docs/extensions/lakebase-vector#upgrade-the-extension-and-indexes).
## New Neon Functions templates
The [Function Registry](https://neon.com/docs/compute/functions/registry/templates) we introduced last week has six new templates, many of them combining [Functions](https://neon.com/docs/compute/functions/overview) with Neon's other backend services. List them and add one to your project from the Neon CLI:
```bash
neon functions templates list
neon functions new mcp-postgres
```
The new templates:
- `mcp-postgres`: an MCP server with tools that read and write a Postgres table
- `telegram-bot`: an AI chat bot that keeps its conversation history in Postgres
- `image-analysis`: an API that describes uploaded images with a vision model on [AI Gateway](https://neon.com/docs/ai-gateway/overview)
- `image-generation`: an API that generates images on AI Gateway and stores them in [Object Storage](https://neon.com/docs/storage/overview)
- `rest-api-postgres`: a REST API for a Postgres table
- `authenticated-api`: an API that only [Managed Better Auth](https://neon.com/docs/auth/overview) users can call
To share your own template, see the [contributing guide](https://github.com/neondatabase/examples/blob/main/registry/CONTRIBUTING.md).
## Drag and drop uploads for Object Storage
You can now upload to [Object Storage](https://neon.com/docs/storage/overview) from the Neon Console by dragging files and folders into a bucket. Open the **Object storage** tab on your branch, select a bucket, and drop your files. You can still use **Upload** to pick files, or **New folder** to create a subfolder. See [Buckets](https://neon.com/docs/storage/buckets).
## HIPAA support for Neon's backend services
[HIPAA compliance](https://neon.com/docs/security/hipaa) now extends to Neon's backend services. In a HIPAA-enabled project, you can now use [Managed Better Auth](https://neon.com/docs/auth/overview), the [Data API](https://neon.com/docs/data-api/get-started), [Functions](https://neon.com/docs/compute/functions/overview), [Object Storage](https://neon.com/docs/storage/overview), [AI Gateway](https://neon.com/docs/ai-gateway/overview), and [Realtime](https://neon.com/docs/realtime/overview) with protected health information (PHI).
If you need a counter-signed copy of the Business Associate Agreement (BAA) for your records, you can now [request one](https://neon.com/baa/signed). See [Business Associate Agreement (BAA)](https://neon.com/docs/security/hipaa#business-associate-agreement-baa).
## Set up your coding agent for Neon
You can now set up your coding agent for Neon with a single prompt. It installs the Neon CLI, signs you in, and adds Neon's agent skills and MCP server:
```text
Set me up for Neon. Fetch https://neon.com/prompts/agent-setup.md and follow it.
```
To check that your agent has the latest Neon skills, run [`neon skills status`](https://neon.com/docs/cli/skills#status), and update any that are outdated:
```bash
neon skills status
neon skills update -y
```
## Agent prompts for Neon's backend services
Adding a Neon backend service to your app now takes one prompt. Each service has a prompt you hand to your coding agent, and the agent installs the Neon CLI, reads Neon's agent skill, links a project with `neon init`, then builds a small working example in your project to show it works.
Copy a prompt from **Set up with your agent** at the top of each service's overview page:
- [Lakebase Postgres](https://neon.com/docs/postgres/overview)
- [Managed Better Auth](https://neon.com/docs/auth/overview)
- [Functions](https://neon.com/docs/compute/functions/overview)
- [Object Storage](https://neon.com/docs/storage/overview)
- [AI Gateway](https://neon.com/docs/ai-gateway/overview)
- [Realtime](https://neon.com/docs/realtime/overview)
## Fixes & improvements
**Data API**
- You can now enable the [Data API](https://neon.com/docs/data-api/get-started) on branches with an [expiration date](https://neon.com/docs/guides/branch-expiration), from the Console or the API. When the branch expires, its Data API is removed with it.
**Managed Better Auth**
- The Managed Better Auth SDK is now [`@neon/auth`](https://neon.com/docs/auth/overview) (previously `@neondatabase/auth`), and the Data API client is `@neon/postgrest-js`. Import paths keep the same subpaths, such as `@neon/auth/next`. For prebuilt sign-in and account UI, use [Better Auth UI](https://neon.com/docs/auth/reference/ui-components), which replaces the deprecated `@neondatabase/auth-ui`.
**Vercel**
- Fixed an issue in the [Neon-Managed Vercel integration](https://neon.com/docs/guides/neon-managed-vercel-integration#environment-variables) where the Managed Better Auth variables (`NEON_AUTH_BASE_URL` and `VITE_NEON_AUTH_URL`) on the **Settings** tab were enabled or disabled based on your project's default branch instead of your production branch.
**Neon MCP server**
- The [Neon MCP Server](https://neon.com/docs/ai/neon-mcp-server) can now manage the Managed Better Auth [OAuth provider plugin](https://neon.com/docs/auth/guides/plugins/oauth-provider): set up the authorization server and manage its OAuth clients, including rotating their secrets. The new tools are in the `neon_auth` category.
**Neon CLI**
- Configure the Managed Better Auth [OAuth provider plugin](https://neon.com/docs/auth/guides/plugins/oauth-provider) from the terminal. `neon neon-auth config oauth-server` enables the server and manages its pages, MCP server URL, and protected resources, and `neon neon-auth oauth-client` creates, updates, rotates, and deletes its clients. See [OAuth server](https://neon.com/docs/cli/neon-auth#config-oauth-server) and [OAuth clients](https://neon.com/docs/cli/neon-auth#oauth-client).
- `neon neon-auth oauth-provider add` and `update` now support Apple and Microsoft, with `--apple-team-id`, `--apple-key-id`, `--microsoft-tenant-id`, and `--oauth-client-secret-file` for reading a secret such as Apple's `.p8` key from a file (Neon CLI 8.14.0).
- `neon init --services data-api` no longer turns on Managed Better Auth for a branch whose Data API uses an external identity provider, such as Clerk or Auth0.
**Regions and networking**
- Added NAT gateway IP addresses and Private Networking VPC endpoint service names in AWS US East (N. Virginia) (`us-east-1`), AWS US East (Ohio) (`us-east-2`), and AWS US West (Oregon) (`us-west-2`). If you allowlist Neon's outbound IPs, add the new addresses from the [Regions](https://neon.com/docs/introduction/regions#nat-gateway-ip-addresses) page, or outbound connections can fail intermittently. If you use Private Networking in these regions, add the new service names from the [Private Networking guide](https://neon.com/docs/guides/neon-private-networking).
**Neon status page**
- The [Neon status page](https://neonstatus.com/) now reports the status of Neon's backend services: the Data API, Managed Better Auth, Object Storage, Functions, and AI Gateway. Each service is listed for the regions where it's available, so you can check whether an issue is affecting a service in your region. See [Neon status](https://neon.com/docs/introduction/status).
**Neon Console**
- We updated the Drizzle Studio integration behind the [**Tables** page](https://neon.com/docs/guides/tables), where you browse and edit your data, to version 1.7.1. This release reworks the schema page, adds support for realtime updates, and fixes an error that occurred after committing a schema rename. For details, see the [Neon Drizzle Studio Integration Changelog](https://github.com/neondatabase/neon-drizzle-studio-changelog/blob/main/CHANGELOG.md).