The code-native video gateway for developers and agents
Route prompts to rendering engines and orchestration models through one OpenAI-compatible API
Route prompts to rendering engines and orchestration models through one OpenAI-compatible API
Experiment with leading LLMs for video orchestration that aren't available via your existing subscription.
Define video in code—HTML with HyperFrames, React with Remotion. The output is linked to an editable artifact you can tweak and render, unlike diffusion-based video models that can't be modified with such precision. .
Route to multiple providers with automatic failover. When one provider is down, requests route to the next available option.
Pay for orchestration tokens, not GPU hours. Transparent pricing per model with no subscriptions or minimum commitments.
Drop-in replacement for the OpenAI SDK. Change the base URL and start generating videos with your existing code.
Get notified when videos complete. Pass webhook_url per request, with retries and signature verification.
Get an API key, load credits, and send your first generation request.
Sign up to get an API key for your app or agent. No credit card required to create an account.
Create accountPurchase credits in your dashboard when you are ready to generate. Credits apply to any orchestration model or rendering engine.
Add creditsSend a prompt with your chosen model and engine. Pipevideo handles provider routing, rendering, and webhook delivery when the video is ready.
Read API docsCreating videos with Claude, Cursor, or Claude Code is not scalable once you leave your machine.
Pipevideo providers handle the hard parts of video generation, like server rendering and agent harnesses, so you can focus on your core use case.
Welcome to code-native video's text-to-video moment.
Install and use Pipevideo with HyperFrames and your chosen LLM.
import { Pipevideo } from '@pipevideo/sdk';
import { NextResponse } from 'next/server';
const client = new Pipevideo({
apiKey: process.env.PIPEVIDEO_API_KEY
});
export async function POST(req: Request) {
const { prompt } = await req.json();
const video = await client.responses.create({
model: 'moonshotai/kimi-k2.5',
engine: 'hyperframes',
input: prompt,
provider: { order: ['pipevideo'] },
});
return NextResponse.json(video);
}Product updates, guides, and insights from the Pipevideo team.
How Pipevideo simplifies video generation by providing a single OpenAI-compatible API for multiple video engines and orchestration models.
Read moreLearn how Pipevideo routes your prompts to the right video generation engine and orchestration model for optimal results.
Read moreHow we built the Pipevideo Rankings dashboard to provide real-time insights into video generation performance and pricing.
Read moreGet your API key and start building with code-driven video.