Skip to main content
The Vercel AI SDK works with Raven out of the box using the @ai-sdk/openai-compatible provider. This gives you access to generateText, streamText, useChat, and all other AI SDK features through your self-hosted Raven gateway.

​
Installation

npm install ai @ai-sdk/openai-compatible

​
Setup

Create a Raven provider using createOpenAICompatible: 
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";

const raven = createOpenAICompatible({
  name: "raven",
  apiKey: "rk_live_abc123...",
  baseURL: "http://localhost:4000/v1",
});

​
Generate Text

import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
import { generateText } from "ai";

const raven = createOpenAICompatible({
  name: "raven",
  apiKey: "rk_live_abc123...",
  baseURL: "http://localhost:4000/v1",
});

const { text } = await generateText({
  model: raven("gpt-4o"),
  prompt: "Explain quantum computing in one paragraph.",
});

console.log(text);
Use any model from your configured providers: 
// OpenAI
const { text } = await generateText({
  model: raven("gpt-4o"),
  prompt: "Hello!",
});

// Anthropic
const { text } = await generateText({
  model: raven("claude-sonnet-4-20250514"),
  prompt: "Hello!",
});

​
Stream Text

import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
import { streamText } from "ai";

const raven = createOpenAICompatible({
  name: "raven",
  apiKey: "rk_live_abc123...",
  baseURL: "http://localhost:4000/v1",
});

const result = streamText({
  model: raven("gpt-4o"),
  prompt: "Write a short story about a robot.",
});

for await (const text of result.textStream) {
  process.stdout.write(text);
}

​
Next.js API Route

Create an API route that streams responses from Raven: 
// app/api/chat/route.ts
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
import { streamText } from "ai";

const raven = createOpenAICompatible({
  name: "raven",
  apiKey: process.env.RAVEN_API_KEY!,
  baseURL: "http://localhost:4000/v1",
});

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

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

  return result.toDataStreamResponse();
}

​
Chat UI with useChat

Pair the API route with the useChat hook for a full chat interface: 
// app/page.tsx
"use client";

import { useChat } from "@ai-sdk/react";
import { useState } from "react";

export default function Chat() {
  const [input, setInput] = useState("");
  const { messages, sendMessage } = useChat();

  return (
    <div>
      {messages.map((message) => (
        <div key={message.id}>
          <strong>{message.role === "user" ? "You" : "AI"}:</strong>
          {message.parts.map((part, i) => {
            if (part.type === "text") {
              return <span key={i}>{part.text}</span>;
            }
          })}
        </div>
      ))}

      <form
        onSubmit={(e) => {
          e.preventDefault();
          sendMessage({ text: input });
          setInput("");
        }}
      >
        <input
          value={input}
          onChange={(e) => setInput(e.target.value)}
          placeholder="Send a message..."
        />
        <button type="submit">Send</button>
      </form>
    </div>
  );
}

​
Function Calling

import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
import { generateText, tool } from "ai";
import { z } from "zod";

const raven = createOpenAICompatible({
  name: "raven",
  apiKey: "rk_live_abc123...",
  baseURL: "http://localhost:4000/v1",
});

const { text, toolResults } = await generateText({
  model: raven("gpt-4o"),
  prompt: "What is the weather in Tokyo?",
  tools: {
    getWeather: tool({
      description: "Get current weather for a city",
      parameters: z.object({
        city: z.string().describe("City name"),
      }),
      execute: async ({ city }) => {
        return { temperature: 22, condition: "sunny" };
      },
    }),
  },
});

​
Environment Variables

Store your Raven virtual key in your environment: 
RAVEN_API_KEY=rk_live_abc123...
Then reference it in your provider setup: 
const raven = createOpenAICompatible({
  name: "raven",
  apiKey: process.env.RAVEN_API_KEY!,
  baseURL: "http://localhost:4000/v1",
});
Replace http://localhost:4000 with your Raven gateway URL if you deployed it to a different host or port.