VIDEO API

AI Video Generation API

Generate, edit, and extend video with Kling, Seedance, Veo, Runway, Hailuo through one REST API.

76 models · async webhooks · pay as you go

76
MODELS
11
PROVIDERS
93
Endpoints
Playground live
Model
Prompt
Slow dolly through a neon-lit night market, rain on the pavement, shallow depth of field
Duration
5s
Aspect ratio
16:9
Resolution
1080p
Mode
text_to_video
Est. cost
$0.27-$2.20 / second

Everything the video endpoint can do

Text to Video

Describe a shot and get finished footage. Prompt, duration, and aspect ratio on one endpoint.

Image to Video

Animate a still frame. Pass a reference image and a motion prompt for controlled camera moves.

Video Editing

Re-cut, restyle, or replace regions in an existing clip without re-rendering the whole shot.

Video Upscale

Take a 480p draft to 1080p or 4K once the edit is locked. Cheaper than generating at full resolution.

Lip Sync

Drive a talking head from an audio track. Works with generated or uploaded footage.

AI Avatar

Render a consistent presenter from a single reference image and a script.

Video models on one key

Seedance/seedance-2.0

Bytedance

$0.27-$2.20 / second

Kling/kling-3.0

Kuaishou

$0.18-$0.91 / second

Veo 3.1/veo-3.1

Google

$2.50 / video

Gemini Omni/gemini-omni-character

Google

Free / video

Grok Imagine

xAI

$0.10-$0.30 / video

Hailuo/hailuo-02-image-to-video-pro

MiniMax

$0.57 / video

HappyHorse/happyhorse-1.0-i2v

Alibaba

$0.24-$0.41 / second

InfiniteTalk/infinitetalk-from-audio

MeiGen-AI

$0.03-$0.12 / second

View all 76 video models
Quickstart

Create a video task

import json
import os
import requests

response = requests.post(
    "https://runapi.ai/api/v1/gemini_omni/text_to_video",
    headers={"Authorization": f"Bearer {os.environ['RUNAPI_API_KEY']}"},
    json=json.loads("{\"model\":\"gemini-omni-flash-1-1\",\"prompt\":\"A presenter walks through a bright studio.\",\"duration_seconds\":4}")
)
response.raise_for_status()
print(response.json())
How it works

Four Steps to Your First Generation

  1. Get Your API Key

    Sign up and copy your key from the dashboard.

  2. Choose a Model

    Pick the model that fits your input and output needs.

  3. Send a Request

    POST to /api/v1/kling/text_to_video with your prompt, model, and parameters.

  4. Get Your Video

    Poll the task or use a webhook, then download your generated video.

Why Developers Choose RunAPI

One Key, All Models

Stop juggling API keys. One integration gives you access to 76 video models across all providers.

15-25% Cost Savings

Our volume agreements with providers mean lower prices than going direct. No markup on top.

Automatic Failover

If a provider goes down, we route to the next best option. Your app stays up.

OpenAI-Compatible

Drop-in replacement for OpenAI SDK. Change one line of code to access any model.

Real-Time Billing

Pay only for what you use. Per-request pricing with no minimums. Track costs per model, per project.

Data Privacy

Our Privacy Policy explains how request data and generated content are processed and retained.

What teams build with it

Marketing Content

Spin up ad variants per audience segment. One prompt template, one key, per-second billing.

Social Media

Vertical clips at volume. Queue hundreds of tasks and collect results over webhooks.

Product Demos

Animate product stills into motion loops without a shoot or a motion designer.

Agent Workflows

Let an agent call video generation as a tool through the MCP server with no custom API code.

RunAPI vs alternatives

Feature RunAPI Runway Direct Replicate
Video models 76 1 provider ~15
Pricing 15-25% below official Official rate Market rate
Async + webhooks Partial
Unified credits
MCP server
Provider failover

Video API questions

Which video models can I access?

Access Kling, Seedance, Veo, Runway, Hailuo, and more with one API key. Browse the model catalog for available versions, capabilities, and prices.

Can I animate images, edit videos, or extend clips?

Yes, with a model that supports the relevant endpoint. Image-to-video, video editing, extension, upscaling, and lip sync have different input requirements; check the selected model’s documentation.

How is video billed?

Rates and billing units vary by model and endpoint. Duration, resolution, and other options can affect the price. Check the catalog rate and request parameters before submitting a task.

How do I receive the generated video?

Video generation runs asynchronously. Submit a request, save the returned task ID, then poll the task endpoint or configure a webhook. The completed task contains the video result.

Which durations and resolutions are supported?

Supported durations, resolutions, and aspect ratios depend on the model and operation. Use the options listed in the endpoint documentation; settings shown in the playground are not available on every model.

How do I start using the Video API?

Sign in, create an API key, and choose a video model. Use the quickstart code or an SDK to submit a request, then retrieve the result by polling or webhook.

Ship video generation this week

One API key for video generation, editing, and extension. Choose a model, check its price, and start building.