Migrate from Vercel AI Gateway
Keep your Vercel AI SDK code, add response caching, detailed analytics, and smart routing. One provider for all models.
Published
Quick Migration
Swap your provider imports—your AI SDK code stays the same:
1- import { openai } from "@ai-sdk/openai";2- import { anthropic } from "@ai-sdk/anthropic";3+ import { generateText } from "ai";4+ import { createLLMGateway } from "@llmgateway/ai-sdk-provider";5
6+ const llmgateway = createLLMGateway({7+ apiKey: process.env.LLM_GATEWAY_API_KEY8+ });9
10const { text } = await generateText({11- model: openai("gpt-5.2"),12+ model: llmgateway("gpt-5.2"),13 prompt: "Hello!"14});1- import { openai } from "@ai-sdk/openai";2- import { anthropic } from "@ai-sdk/anthropic";3+ import { generateText } from "ai";4+ import { createLLMGateway } from "@llmgateway/ai-sdk-provider";5
6+ const llmgateway = createLLMGateway({7+ apiKey: process.env.LLM_GATEWAY_API_KEY8+ });9
10const { text } = await generateText({11- model: openai("gpt-5.2"),12+ model: llmgateway("gpt-5.2"),13 prompt: "Hello!"14});The key difference: one provider, one API key, all models—with caching and analytics built in.
Migration Steps
1. Get Your doteb API Key
Sign up at doteb.com/signup and create an API key from your dashboard.
2. Install the doteb AI SDK Provider
Install the native doteb provider for the Vercel AI SDK:
1pnpm add @llmgateway/ai-sdk-provider1pnpm add @llmgateway/ai-sdk-providerThis package provides full compatibility with the Vercel AI SDK and supports all doteb features.
3. Update Your Code
Basic Text Generation
1// Before (Vercel AI Gateway with native providers)2import { openai } from "@ai-sdk/openai";3import { anthropic } from "@ai-sdk/anthropic";4import { generateText } from "ai";5
6const { text: openaiText } = await generateText({7 model: openai("gpt-4o"),8 prompt: "Hello!",9});10
11const { text: claudeText } = await generateText({12 model: anthropic("claude-3-5-sonnet-20241022"),13 prompt: "Hello!",14});15
16// After (doteb - single provider for all models)17import { createLLMGateway } from "@llmgateway/ai-sdk-provider";18import { generateText } from "ai";19
20const llmgateway = createLLMGateway({21 apiKey: process.env.LLM_GATEWAY_API_KEY,22});23
24const { text: openaiText } = await generateText({25 model: llmgateway("gpt-4o"),26 prompt: "Hello!",27});28
29const { text: claudeText } = await generateText({30 model: llmgateway("anthropic/claude-3-5-sonnet-20241022"),31 prompt: "Hello!",32});1// Before (Vercel AI Gateway with native providers)2import { openai } from "@ai-sdk/openai";3import { anthropic } from "@ai-sdk/anthropic";4import { generateText } from "ai";5
6const { text: openaiText } = await generateText({7 model: openai("gpt-4o"),8 prompt: "Hello!",9});10
11const { text: claudeText } = await generateText({12 model: anthropic("claude-3-5-sonnet-20241022"),13 prompt: "Hello!",14});15
16// After (doteb - single provider for all models)17import { createLLMGateway } from "@llmgateway/ai-sdk-provider";18import { generateText } from "ai";19
20const llmgateway = createLLMGateway({21 apiKey: process.env.LLM_GATEWAY_API_KEY,22});23
24const { text: openaiText } = await generateText({25 model: llmgateway("gpt-4o"),26 prompt: "Hello!",27});28
29const { text: claudeText } = await generateText({30 model: llmgateway("anthropic/claude-3-5-sonnet-20241022"),31 prompt: "Hello!",32});Streaming Responses
1import { createLLMGateway } from "@llmgateway/ai-sdk-provider";2import { streamText } from "ai";3
4const llmgateway = createLLMGateway({5 apiKey: process.env.LLM_GATEWAY_API_KEY,6});7
8const { textStream } = await streamText({9 model: llmgateway("anthropic/claude-3-5-sonnet-20241022"),10 prompt: "Write a poem about coding",11});12
13for await (const text of textStream) {14 process.stdout.write(text);15}1import { createLLMGateway } from "@llmgateway/ai-sdk-provider";2import { streamText } from "ai";3
4const llmgateway = createLLMGateway({5 apiKey: process.env.LLM_GATEWAY_API_KEY,6});7
8const { textStream } = await streamText({9 model: llmgateway("anthropic/claude-3-5-sonnet-20241022"),10 prompt: "Write a poem about coding",11});12
13for await (const text of textStream) {14 process.stdout.write(text);15}Using in Next.js API Routes
1// app/api/chat/route.ts2import { createLLMGateway } from "@llmgateway/ai-sdk-provider";3import { streamText } from "ai";4
5const llmgateway = createLLMGateway({6 apiKey: process.env.LLM_GATEWAY_API_KEY,7});8
9export async function POST(req: Request) {10 const { messages } = await req.json();11
12 const result = await streamText({13 model: llmgateway("gpt-4o"),14 messages,15 });16
17 return result.toDataStreamResponse();18}1// app/api/chat/route.ts2import { createLLMGateway } from "@llmgateway/ai-sdk-provider";3import { streamText } from "ai";4
5const llmgateway = createLLMGateway({6 apiKey: process.env.LLM_GATEWAY_API_KEY,7});8
9export async function POST(req: Request) {10 const { messages } = await req.json();11
12 const result = await streamText({13 model: llmgateway("gpt-4o"),14 messages,15 });16
17 return result.toDataStreamResponse();18}Alternative: Using OpenAI SDK Adapter
If you prefer not to install a new package, you can use @ai-sdk/openai with a custom base URL:
1import { createOpenAI } from "@ai-sdk/openai";2import { generateText } from "ai";3
4const llmgateway = createOpenAI({5 baseURL: "https://api.doteb.com/v1",6 apiKey: process.env.LLM_GATEWAY_API_KEY,7});8
9const { text } = await generateText({10 model: llmgateway("gpt-4o"),11 prompt: "Hello!",12});1import { createOpenAI } from "@ai-sdk/openai";2import { generateText } from "ai";3
4const llmgateway = createOpenAI({5 baseURL: "https://api.doteb.com/v1",6 apiKey: process.env.LLM_GATEWAY_API_KEY,7});8
9const { text } = await generateText({10 model: llmgateway("gpt-4o"),11 prompt: "Hello!",12});4. Update Environment Variables
1# Remove individual provider keys (optional - can keep as backup)2# OPENAI_API_KEY=sk-...3# ANTHROPIC_API_KEY=sk-ant-...4
5# Add doteb key6export LLM_GATEWAY_API_KEY=llmgtwy_your_key_here1# Remove individual provider keys (optional - can keep as backup)2# OPENAI_API_KEY=sk-...3# ANTHROPIC_API_KEY=sk-ant-...4
5# Add doteb key6export LLM_GATEWAY_API_KEY=llmgtwy_your_key_hereModel Name Format
doteb supports two model ID formats:
Root Model IDs (without provider prefix) - Uses smart routing to automatically select the best provider based on uptime, throughput, price, and latency:
1gpt-4o2claude-3-5-sonnet-202410223gemini-1.5-pro1gpt-4o2claude-3-5-sonnet-202410223gemini-1.5-proProvider-Prefixed Model IDs - Routes to a specific provider with automatic failover if uptime drops below 90%:
1openai/gpt-4o2anthropic/claude-3-5-sonnet-202410223google-ai-studio/gemini-1.5-pro1openai/gpt-4o2anthropic/claude-3-5-sonnet-202410223google-ai-studio/gemini-1.5-proFor more details on routing behavior, see the routing documentation.
Model Mapping Examples
| Vercel AI SDK | doteb |
|---|---|
openai("gpt-4o") | llmgateway("gpt-4o") |
anthropic("claude-3-5-sonnet-20241022") | llmgateway("claude-3-5-sonnet-20241022") |
google("gemini-1.5-pro") | llmgateway("gemini-1.5-pro") |
Check the models page for the full list of available models.
Tool Calling
doteb supports tool calling through the AI SDK:
1import { createLLMGateway } from "@llmgateway/ai-sdk-provider";2import { generateText, tool } from "ai";3import { z } from "zod";4
5const llmgateway = createLLMGateway({6 apiKey: process.env.LLM_GATEWAY_API_KEY,7});8
9const { text, toolResults } = await generateText({10 model: llmgateway("gpt-4o"),11 tools: {12 weather: tool({13 description: "Get the weather for a location",14 parameters: z.object({15 location: z.string(),16 }),17 execute: async ({ location }) => {18 return { temperature: 72, condition: "sunny" };19 },20 }),21 },22 prompt: "What's the weather in San Francisco?",23});1import { createLLMGateway } from "@llmgateway/ai-sdk-provider";2import { generateText, tool } from "ai";3import { z } from "zod";4
5const llmgateway = createLLMGateway({6 apiKey: process.env.LLM_GATEWAY_API_KEY,7});8
9const { text, toolResults } = await generateText({10 model: llmgateway("gpt-4o"),11 tools: {12 weather: tool({13 description: "Get the weather for a location",14 parameters: z.object({15 location: z.string(),16 }),17 execute: async ({ location }) => {18 return { temperature: 72, condition: "sunny" };19 },20 }),21 },22 prompt: "What's the weather in San Francisco?",23});Self-Hosting doteb
If you prefer self-hosting, use the self-hosting guide or the deployment package supplied for your environment.
This gives you the same managed experience with full control over your infrastructure.
Need Help?
- Browse available models at doteb.com/models
- Read the API documentation
- Contact support at contact@doteb.com