Open-source status page, incident response and uptime monitoring
TypeScript alertingincident-managementmcpmcp-servermonitoringmonitoring-as-codeobservabilityon-callopen-sourcesrestatus-pagestatuspagesynthetic-monitoringterraformtinybirdtursouptimeuptime-checkeruptime-monitor
docs: add Neon AI Gateway configuration section (#2446)
Dominik K.9cccdf136f25
diff --git a/apps/web/src/content/pages/docs/guides/self-hosting-openstatus.mdx b/apps/web/src/content/pages/docs/guides/self-hosting-openstatus.mdxindex b60120de6..c5938429b 100644--- a/apps/web/src/content/pages/docs/guides/self-hosting-openstatus.mdx+++ b/apps/web/src/content/pages/docs/guides/self-hosting-openstatus.mdx@@ -263,7 +263,7 @@ openstatus ships an in-dashboard AI assistant. It is **off by default** when sel### Option 1: OpenAI-compatible endpoint (bring your own model)-Use any OpenAI-compatible API — [NVIDIA NIM](https://build.nvidia.com/), vLLM, Ollama, OpenRouter, [Neon AI Gateway](https://neon.com/docs/ai-gateway/overview), LM Studio, or a private gateway. This is the recommended path for self-hosting: the model and key stay on your own infrastructure.+Use any OpenAI-compatible API — [NVIDIA NIM](https://build.nvidia.com/), vLLM, Ollama, OpenRouter, Neon AI Gateway, LM Studio, or a private gateway. This is the recommended path for self-hosting: the model and key stay on your own infrastructure.```envAI_BASE_URL=https://integrate.api.nvidia.com/v1@@ -282,15 +282,19 @@ AI_BASE_URL=http://localhost:11434/v1AI_MODEL=llama3.1```-Each Neon branch has its own [Neon AI Gateway](https://neon.com/docs/ai-gateway/overview) host, so `AI_BASE_URL` is that host plus `/v1` and `AI_API_KEY` is a Neon credential with the `ai_gateway:invoke` scope:+#### Example: Neon AI Gateway++[Neon AI Gateway](https://neon.com/docs/ai-gateway/overview) serves an OpenAI-compatible API, so it goes through the same three variables. Every Neon branch has its own gateway host, which the Neon console shows as `NEON_AI_GATEWAY_BASE_URL` next to a `NEON_AI_GATEWAY_TOKEN` credential. The host is bare, so add `/v1` when you copy it, and give the credential the `ai_gateway:invoke` scope.```env-AI_BASE_URL=https://br-winter-pond-aptw82ef-api.ai.c-2.us-east-2.aws.neon.tech/v1-AI_API_KEY=nt_live_xxxxx+AI_BASE_URL=<NEON_AI_GATEWAY_BASE_URL>/v1+AI_API_KEY=<NEON_AI_GATEWAY_TOKEN>AI_MODEL=gpt-5-mini```-Neon's own docs call these two values `NEON_AI_GATEWAY_BASE_URL` and `NEON_AI_GATEWAY_TOKEN`, and the base URL they show is the bare host, so add `/v1` when you copy it. Pick an `AI_MODEL` from the [Neon model catalog](https://neon.com/docs/ai-gateway/models) that lists `chat/completions` among its endpoints. AI Gateway is in beta, requires a paid Neon plan, and runs only in AWS US East (Ohio) (`aws-us-east-2`).+Any entry in the [Neon model catalog](https://neon.com/docs/ai-gateway/models) that lists `chat/completions` among its endpoints works as `AI_MODEL`, and the `gpt-5-mini` above is one example rather than a default. Pick a model that supports tool calling. Neon does not record that per model, so check the flag on [Models.dev](https://models.dev/providers/neon/) first. This path has not been validated through a complete assistant workflow, so exercise a real monitor or status-page change before you depend on it.++<Aside type="note">AI Gateway is in beta, requires a paid Neon plan, and runs only in AWS US East (Ohio) (`aws-us-east-2`).</Aside>### Option 2: Vercel AI Gateway