---
title: Getting Started
product: vercel
url: /docs/ai-gateway/getting-started
canonical_url: "https://vercel.com/docs/ai-gateway/getting-started"
last_updated: 2026-07-28
type: tutorial
prerequisites:
  - /docs/ai-gateway
related:
  - /docs/ai-gateway/getting-started/text
  - /docs/ai-gateway/getting-started/image
  - /docs/ai-gateway/getting-started/video
  - /docs/ai-gateway/getting-started/realtime
  - /docs/ai-gateway/getting-started/speech
summary: Get started with AI Gateway by generating text, images, video, speech, or transcriptions, or by building realtime voice agents.
install_vercel_plugin: npx plugins add vercel/vercel-plugin
---

# Getting Started with AI Gateway

Choose a quickstart to set up a project and make your first request:


<!-- docsgraph:related -->
## Related pages

> **For AI agents:** Follow these links to understand how this page connects to the rest of the Vercel ecosystem. For the full cross-link map (inbound, outbound, prerequisites, and semantic neighbors), see the .graph.md link below.

- [How to build AI Agents with Vercel and the AI SDK](https://vercel.com/kb/guide/how-to-build-ai-agents-with-vercel-and-the-ai-sdk?from=related) — Learn how to build, deploy, and scale AI agents on Vercel using the AI SDK. This guide covers calling LLMs, defining too
- [Text Generation](https://vercel.com/docs/ai-gateway/modalities/text-generation?from=related) — Generate and stream text from hundreds of models through AI Gateway, with tool calling and structured output.
- [Text to Speech](https://vercel.com/docs/ai-gateway/modalities/text-to-speech?from=related) — Generate spoken audio from text with speech models through Vercel AI Gateway.
- [Image Generation](https://vercel.com/docs/ai-gateway/modalities/image-generation?from=related) — Generate and edit images using AI models through Vercel AI Gateway with support for multiple providers and modalities.
- [Text Generation](https://vercel.com/docs/ai-gateway/sdks-and-apis/responses/text-generation?from=related) — Generate text responses with the OpenAI Responses API through AI Gateway.
- [Modalities](https://vercel.com/docs/ai-gateway/modalities?from=related) — The inputs and outputs AI Gateway models work with: text, image, and video generation, speech to text, text to speech, r

Full cross-link map for this page: [/docs/ai-gateway/getting-started.graph.md](/docs/ai-gateway/getting-started.graph.md)
<!-- /docsgraph:related -->

**Text Generation**: Generate and stream text with GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, Llama 4, and 100+ more models. [Learn more →](/docs/ai-gateway/getting-started/text)

**Image Generation**: Create images from text prompts or edit existing images with Flux 2 Flex, Recraft V3, Imagen, and more. [Learn more →](/docs/ai-gateway/getting-started/image)

**Video Generation**: Create videos from text prompts, images, or video input with Veo 3.1, KlingAI, Wan, Grok Imagine Video, and more. Run them over a single request or as background jobs. [Learn more →](/docs/ai-gateway/getting-started/video)

**Realtime**: Build low-latency, speech-to-speech voice agents that listen and respond over WebSockets. [Learn more →](/docs/ai-gateway/getting-started/realtime)

**Speech**: Generate spoken audio from text and transcribe audio back to text with tts-1, Whisper, and more. [Learn more →](/docs/ai-gateway/getting-started/speech)


---

[View full sitemap](/docs/sitemap)