GPT-4o
GPT-4o is OpenAI's first natively multimodal "omni" model, unifying text, audio, image, and video processing within a single end-to-end trained architecture and delivering audio response times averaging 320 milliseconds, comparable to human conversational latency.
File InputImplicit CachingTool UseVision (Image)Web Search
index.ts
import { streamText } from 'ai'
const result = streamText({ model: 'openai/gpt-4o', prompt: 'Why is the sky blue?'})Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
 Azure | 128K | 0.7s | 66tps | $2.50/M | $10.00/M | Read:$1.25/M Write:— | $14/K + input costs | — | +3 | 05/13/2024 | ||
 OpenAI | 128K | 0.9s | 70tps | $2.50/M | $10.00/M | Read:$1.25/M Write:— | $10.00/K + input costs | — | +3 | 05/13/2024 |