Skip to main content
Neon Docs

Search documentation

Type to search this documentation.

Get branch AI Gateway endpoint

GET/projects/{project_id}/branches/{branch_id}/ai_gatewayGet branch AI Gateway endpoint

Returns the AI Gateway endpoint host for the specified branch, used to render code-snippet base URLs. A 200 response means the branch is registered and this region serves the AI gateway. A 404 response includes a reason field indicating why the gateway is unavailable.

Note: This endpoint is currently in Beta.

Parameters

project_idstringpathrequired

The Neon project ID

pattern ^[a-z0-9-]{1,60}$

branch_idstringpathrequired

The Neon branch ID

pattern ^[a-z0-9-]{1,60}$

Responses

200AI Gateway is enabled for this branchapplication/json
objectBranchAiGateway
base_urlstring · urirequired

The AI-gateway endpoint root for this branch — an OpenAI-compatible base URL. No dialect path is included; clients append the route (e.g. `/ai-gateway/openai/v1/responses`) themselves.

enabledbooleanrequired

Always `true` in 200 responses. Present for forward compatibility, mirroring BranchStorage.enabled.

Example response
{
  "base_url": "https://br-cool-moon-42-api.ai.c-2.local.neon.build",
  "enabled": true
}
404AI Gateway is not available for this branch, or the project/branch was not found. The body is always `BranchAiGatewayNotEnabled` — see `reason` for the exact cause. application/json
objectBranchAiGatewayNotEnabled
codestringrequired
messagestringrequired
reasonstringrequired

Machine-readable reason why the AI gateway is unavailable: - `ai_gateway_unavailable`: the project's region/cell has no AI gateway configured. - `branch_not_found`: the project or branch does not exist, or the caller does not have access to it.

one of "ai_gateway_unavailable", "branch_not_found"

Example response
{
  "code": "AI_GATEWAY_NOT_ENABLED",
  "message": "string",
  "reason": "ai_gateway_unavailable"
}
defaultGeneral Error. The request may or may not be safe to retry, depending on the HTTP method, response status code, and whether a response was received. - If no response is returned from the API, a network error or timeout likely occurred. - In some cases, the request may have reached the server and been successfully processed, but the response failed to reach the client. As a result, retrying non-idempotent requests can lead to unintended results. The following HTTP methods are considered non-idempotent: `POST`, `PATCH`, `DELETE`, and `PUT`. Retrying these methods is generally **not safe**. The following methods are considered idempotent: `GET`, `HEAD`, and `OPTIONS`. Retrying these methods is **safe** in the event of a network error or timeout. Any request that returns a `503 Service Unavailable` response is always safe to retry. Any request that returns a `423 Locked` response is safe to retry. `423 Locked` indicates that the resource is temporarily locked, for example, due to another operation in progress. application/json
objectGeneralError
codestringrequired

default ""

messagestringrequired

Error message

request_idstring

Unique identifier for the request, useful for debugging. You can set this value manually by including an `X-Request-ID` header in the request. If not provided, the value will be generated automatically.

Example response
{
  "code": "",
  "message": "string",
  "request_id": "string"
}
Documentation menu