Skip to main content

Pricing & Tokens: Videos, Images, and Models Explained

AI Studio - Token usage breakdown

Mikaela Lasig avatar
Written by Mikaela Lasig
Updated over a week ago

Pricing breakdown by: Tokens, Videos, Images

  • Free: 336 tokens; 4 videos (5s) / 2 videos (10s) / 14 images

  • Plus: 2,000 tokens; 38 videos (5s) / 19 videos (10s) / 118 images

  • Pro: 12,000 tokens; 238 videos (5s) / 119 videos (10s) / 743 images

  • Max: 40,000 tokens; 798 videos (5s) / 399 videos (10s) / 2,493 images


AI models Explained: Ask the agent to use them if you want to test

Image Generation

  • OpenAI GPT-Image-1 – quick product mockups with good product consistency.

  • MidJourney Imagine – creative lifestyle and mood shots, strong aesthetics. less control.

  • Runway Gen-4 Image – clean, consistent product edits and simple variations.

  • Flux Pro Kontext – product image editing, add overlay text, or background swaps.

Try-On

  • Fashn – fast virtual try-ons at different speed/quality trade-offs.

  • Kling V1.5 Kolors Try-On – realistic color swaps.

Image to Video

  • Runway Gen-4 Turbo – fast product videos with accurate frame consistency.

  • Runway Gen-3 Turbo – more controlled first/last frame product alignment.

  • Kling v1.6 - fast and best for any video generation; product turn and consistent animated image.

  • Kling v1.6 Multi Images - supports up to 4 images; humans can interact with the product; multiple products in a video.

  • Kling v2 - great for any video generation

  • Kling v2.1 – fast for any video generation

  • Seedance V1 Pro – for 1080p product showcase videos with accurate motion.

  • Seedance V1 Lite – control over video start and video end frames; quick

Video Generation (Advanced)

  • VEO-2 – supports low-quality images with strong realism.

  • VEO-3 – product videos, human holding products with audio.

  • VEO-3 Fast – for quicker versions of VEO-3, slightly less sharp.

Vendor

Model / Mode

Input

Type

Duration

Resolution/Quality

Tokens

RunwayML

Gen-4 Turbo

Text→Video

5s

Standard

50

10s

Standard

100

Gen-3a Turbo

Text→Video

5s

Standard

32

10s

Standard

64

Gen-4 Aleph

Video→Video

Flat

30

Gen-4 Image

Image→
Image

16

OpenAI

GPT-Image-1

Image→
Image or Text → Image

Low

2

Medium

8

High

34

MidJourney

Imagine

Text→Image

9

Kling

v1 / Std

Image→
Image

5s

Std

28

10s

Std

56

v1 / Pro

Image→
Image

5s

Pro

98

10s

Pro

196

v1.5 / Std

Image→
Image

5s

Std

56

10s

Std

112

v1.5 / Pro

Image→
Image

5s

Pro

98

10s

Pro

196

v1.6 / Std

Image→
Image

5s

Std

56

10s

Std

112

v1.6 / Pro

Image→
Image

5s

Pro

98

10s

Pro

196

v2 Master

Image→
Image

5s

280

10s

560

v2.1 Std (missing before)

Image→
Image

5s

Std

56

10s

Std

112

v2.1 Pro (missing before)

Image→
Image

5s

Pro

98

10s

Pro

196

v2.1 Master

Image→
Image

5s

280

10s

560

Fashn

Performance / Balanced / Quality

Try-On

15

Fal

Bria Product Shot

Image→
Image

8

Thera Upscale

Image→
Upscale

3

Aura SR

Image→SR

2

Kling V1.5 Kolors Try-On

Try-On

14

Flux Pro Kontext (low)

Text/Image→
Image

8

Flux Pro Kontext (high)

Text/Image→
Image

16

VEO-2

Video

per sec

100

VEO-3

Video

per sec

w/o audio

40

VEO-3

Video

per sec

w/ audio

80

VEO-3 Fast

Video

per sec

w/o audio

20

VEO-3 Fast

Video

per sec

w/ audio

30

Seedance V1 Pro

Image→Video

per sec

30

Seedance V1 Lite

Image→Video

per sec

8

Did this answer your question?