Vercel AI SDK (gateway)

Route Vercel AI SDK calls through the Respan gateway to use 250+ models from different providers. Only your RESPAN_API_KEY is needed — no separate provider keys required.

Setup

Install packages

$ npm install ai @ai-sdk/openai @respan/respan @respan/instrumentation-vercel

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

No OPENAI_API_KEY needed — the Respan gateway handles provider authentication.

Point a provider at the Respan gateway

1 import { createOpenAI } from "@ai-sdk/openai";
2 import { generateText } from "ai";
3 
4 const provider = createOpenAI({
5   apiKey: process.env.RESPAN_API_KEY!,
6   baseURL: "https://api.respan.ai/api",
7 });
8 
9 const result = await generateText({
10   model: provider("gpt-4.1-nano"),
11   prompt: "Tell me a joke about AI",
12   experimental_telemetry: { isEnabled: true },
13 });
14 console.log(result.text);

Switch models

Change the model parameter to use 250+ models from different providers through the same gateway.

1 const provider = createOpenAI({
2   apiKey: process.env.RESPAN_API_KEY!,
3   baseURL: "https://api.respan.ai/api",
4 });
5 
6 const r1 = await generateText({ model: provider("gpt-4.1-nano"), prompt: "Hello" });
7 const r2 = await generateText({ model: provider("claude-sonnet-4-5-20250929"), prompt: "Hello" });
8 const r3 = await generateText({ model: provider("deepseek/deepseek-chat"), prompt: "Hello" });

See the full model list.

1	import { createOpenAI } from "@ai-sdk/openai";
2	import { generateText } from "ai";
3
4	const provider = createOpenAI({
5	apiKey: process.env.RESPAN_API_KEY!,
6	baseURL: "https://api.respan.ai/api",
7	});
8
9	const result = await generateText({
10	model: provider("gpt-4.1-nano"),
11	prompt: "Tell me a joke about AI",
12	experimental_telemetry: { isEnabled: true },
13	});
14	console.log(result.text);