Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.xenovia.io/llms.txt

Use this file to discover all available pages before exploring further.

​
Setup

npm install ai @ai-sdk/openai

import { createOpenAI } from "@ai-sdk/openai"

const xenovia = createOpenAI({
  apiKey: process.env.XENOVIA_API_KEY,
  baseURL: `https://runtime.xenovia.io/a/${process.env.XENOVIA_PROXY_ID}/openai/v1`
})

const model = xenovia("gpt-4o-mini")

​
Streaming text

import { streamText } from "ai"

const { textStream } = streamText({
  model,
  messages: [{ role: "user", content: "Explain AI governance in plain English" }]
})

for await (const chunk of textStream) {
  process.stdout.write(chunk)
}
Xenovia stamps X-Xenovia-Session-Id and X-Xenovia-Trace-Id into the response headers before the first token, so streaming traces are always correlated correctly.

​
Next.js App Router route handler

// app/api/chat/route.ts
import { streamText } from "ai"
import { createOpenAI } from "@ai-sdk/openai"
import { randomUUID } from "crypto"

export async function POST(req: Request) {
  const { messages, sessionId } = await req.json()

  const xenovia = createOpenAI({
    apiKey: process.env.XENOVIA_API_KEY,
    baseURL: `https://runtime.xenovia.io/a/${process.env.XENOVIA_PROXY_ID}/openai/v1`,
    headers: {
      // Use a stable session ID from the client to group conversation turns
      "X-Xenovia-Session-Id": sessionId ?? randomUUID(),
      // Tag traces with application context
      "X-Xenovia-Property-route": "chat",
    }
  })

  const result = streamText({
    model: xenovia("gpt-4o-mini"),
    messages
  })

  return result.toDataStreamResponse()
}

​
Tool calling

Tool schemas are forwarded to the upstream LLM. The Xenovia request-stage policy evaluates input.tool_names before the call reaches the model. 
import { streamText, tool } from "ai"
import { z } from "zod"

const result = streamText({
  model,
  messages: [{ role: "user", content: "What is the weather in London?" }],
  tools: {
    getWeather: tool({
      description: "Get the weather for a location",
      parameters: z.object({ location: z.string() }),
      execute: async ({ location }) => ({ temperature: "15°C", location })
    })
  }
})

​
Session tracking

Pass a stable session ID to group all turns of a chat conversation. The Vercel AI SDK does not add session IDs automatically — provide one per conversation from your application layer. 
const xenovia = createOpenAI({
  apiKey: process.env.XENOVIA_API_KEY,
  baseURL: `https://runtime.xenovia.io/a/${process.env.XENOVIA_PROXY_ID}/openai/v1`,
  headers: {
    "X-Xenovia-Session-Id": conversationId,  // stable ID from your DB or cookie
    "X-Xenovia-Session-Path": `users/${userId}/conversations`
  }
})

​
Handling policy blocks

When a request is blocked, the runtime returns 403. Handle it at the route level before returning the stream response. 
try {
  const result = streamText({ model, messages })
  return result.toDataStreamResponse()
} catch (error: any) {
  if (error?.status === 403) {
    return new Response(
      JSON.stringify({ error: "Request blocked by policy" }),
      { status: 403, headers: { "Content-Type": "application/json" } }
    )
  }
  throw error
}
The Vercel AI SDK uses persistent connections by default. Subsequent requests within the same server instance have lower latency because the TCP connection to Xenovia is reused.