The inference engine.For multimodal AI.

The most bleeding-edge engine for optimized multimodal models. Purpose-built for image, video, audio, and vision — the workloads defining the next decade of AI.

Get started for free Explore the API

Partnership with

60+ models. One interface

View all the models

Nano banana 2.0Google

Seedance 2.0ByteDance

GPT Image 2Open AI

Happyhorse 1.0Alibaba

Flux 2Black Forest Labs

Sam3Meta

Uni 1Luma labs

Eleven V3elleven labs

Ideogram 4Ideogram

LTX 2.3Lightricks

Powerful host of APIs

Reserved capacity, private endpoints, compliance packages — available as an add-on for teams operating at serious scale.

Get started

Cursor

# Submit

curl https://api.tryinfer.com/v2/inference/seedance-2.0-pro/image-to-video \

-H "Authorization: Bearer $INFER_API_KEY" \

-H "Content-Type: application/json" \

-d '{

"input": {

"image_url": "https://s3.amazonaws.com/images.cocodataset.org/val2017/000000254814.jpg",

"prompt": "subtle parallax, soft wind",

"duration_seconds": "5",

"aspect_ratio": "16:9"

}

# → {"request_id": "..."}

available.pystreaming

import infer

client = infer.Client()

# Initialize with your API key

response = client.image_to_video.create(

image_url="https://example.com/photo.jpg",

prompt="gentle motion, cinematic",

)

Try it now

Purpose-built for image, video, audio, and vision — the workloads defining the next decade of AI.

Get started

ModelKling-3-pro

Prompt

Recolor the scene to dramatic golden-hour sunset lighting — warm amber light raking across the cherry blossoms, long cinematic shadows down the stairway, and a soft volumetric haze catching behind the passing tram. Hold the two figures' poses and the framing exactly; push the sky toward a deep dusk gradient while keeping natural skin tones and the green of the grass intact.

Duration5s

Res720p