Kling
3 models
Kuaishou's video models. Kling 3.0 renders at 4, 8 or 12 seconds; the 2.5 Turbo Pro and 2.6 rows run on Kling's own 5- and 10-second steps.
- Kling 3.0
- from 140 credits
- Kling 2.6
- from 138 credits
- Kling 2.5 Turbo Pro
- from 105 credits
Model directory
Compare AI models for video, images and music
Compare AI models by what you want to make: a video from text, a new image from a reference photo, or a song from an idea. Check live starting prices, browse model guides and open the matching studio when you are ready.
- 18 models
- 10 model families
- Prices read live, not typed in
Cheapest way in
- AI models for video generationGrok Imagine 1.5from 24 credits
- Image modelsNano Bananafrom 10 credits
- Music modelsSuno V6from 30 credits
The lowest-priced model in each group, at its smallest size and shortest length. Enough to test a prompt before spending on a full render.
AI models for video generation
Text-to-video and image-to-video. Prices below are the cheapest combination of resolution and length each model offers; picking a longer clip or a higher resolution raises the cost before you generate, never after.
Seedance
2 models
ByteDance's video family. Seedance 2.5 is the newest, and 2.0 is the lower-priced pass for testing a prompt before a full render.
- Seedance 2.5
- from 280 credits
- Seedance 2.0
- from 190 credits
Grok
1 model
xAI's Imagine video model. A 4-second clip is 24 credits at 480p and 45 at 720p, the lowest video price here, so it is the one to iterate on before a heavier model. Image-to-video only, with no 1080p tier.
- Grok Imagine 1.5
- from 24 credits
Veo
1 model
Google DeepMind's Veo, in its 3.1 Fast configuration.
- Veo 3.1 Fast
- from 150 credits
MiniMax
1 model
MiniMax's Hailuo H3, with separate text-to-video and image-to-video entry points.
- MiniMax H3
- from 160 credits
HappyHorse
1 model
HappyHorse 1.1, a stylised video model sitting between the fast and the premium tiers on price.
- HappyHorse 1.1
- from 225 credits
Image models
Compare AI models for text-to-image and image-to-image work. Most families offer both directions; upload reference photos when your subject or layout already exists, then describe the changes you want.
Seedream
3 models
ByteDance's image family. Every row has a matching image-to-image variant that takes up to 10 reference images, so an edit keeps the look of what you feed it.
- Seedream 5.0 Pro
- from 18 credits
- Seedream 4.5
- from 17 credits
- Seedream 5.0 Lite
- from 14 credits
3 models
Google's Nano Banana line. Nano Banana 2 for everyday work, Pro when you need the extra detail, and the original as the cheapest way to iterate on a prompt.
- Nano Banana Pro
- from 45 credits
- Nano Banana 2
- from 20 credits
- Nano Banana
- from 10 credits
OpenAI
2 models
GPT Image 2 and 1.5. The 1.5 rows let you choose a medium or high quality tier at generation time and price each one separately; both generations do text-to-image and image-to-image.
- GPT Image 2
- from 15 credits
- GPT Image 1.5
- from 10 credits
Music models
Turn an idea into a song with AI models for music. Start with a genre, mood and subject, or bring your own lyrics. Preview vocals and instrumentals in the song studio; check full-song access on the pricing page.
Suno
1 model
Suno V6 writes and performs the whole track — lyrics, vocals and instrumental — from a single description.
- Suno V6
- from 30 credits
Browse by what you want to do
Compare AI models by task when the brand name is not your starting point. These guides cover editing an existing image and turning a still into a video, with supported inputs and live credit costs. Choose a guide, check the options and continue to the studio; generation spends credits.
Image to image
Image models
Start from a picture instead of a blank prompt: upload it, describe the change, and get a new version back — a different style, a fixed detail, a cleaner background. The guide compares every model that accepts a reference image.
- Models that do this
- 8
- Cheapest run
- from 10 credits