Every top model, one canvas
The best model changes every few months. Treza puts them all in one picker, on one credit balance, behind one API, so switching is a dropdown, not a migration.
Video models
Cinematic shots, story-length clips, and reference-driven campaigns. Pick per shot, or run the same prompt across two models and compare.
Veo 3.1
Cinematic hero shots with synced dialogue and sound.
View modelVeo 3.1 Fast
Fast drafts, prompt exploration, and batch social clips.
View modelVeo 3.1 Lite
Affordable Veo clips with audio, at volume.
View modelKling 3.0 Pro
Dance, sport, and action with consistent characters.
View modelSeedance 2.0
Consistent products and characters across whole campaigns.
View modelSeedance 2.5
Long single-take clips and daily short-form volume.
View modelSeedance 1.5 Pro
Low-cost reference-driven clips and silent drafts.
View modelGrok Imagine
High-volume drafts, memes, and clips from real photos.
View modelGrok Imagine 1.5
Grok Imagine ideas finished at up to 1080p.
View modelGrok Imagine 1.5 Lite
Cheap, fast drafts of Grok Imagine ideas.
View modelHeyGen Video
Fast, low-cost drafts, variations, and social clips.
View modelSeedance 2.0 Fast
Seedance 2.0 quality for drafts and volume work.
View modelSeedance 2.0 Mini
Hook tests, storyboards, and high-volume drafts.
View modelHailuo 3 Max
Quick clips that start and land on your frames.
View modelWan 2.7
People-led clips built from real photos.
View modelWan 3.0
Long single takes, from 2 to 30 seconds.
View modelHappyHorse 1.1
Reference-driven clips up to 15 seconds in seven formats.
View modelHailuo 3
Controlled prompts and legible brand text.
View modelRunway Gen-4.5
Cinematic shot craft with reproducible iteration.
View modelFLUX.3 Video
Long takes, keyframe control, and extending footage.
View modelKling Video O1
Everyday clips and scheduled pipelines on a budget.
View modelKling 3.0 Standard
Kling motion for drafts and volume, at half the Pro price.
View modelHailuo 2.3
Silent 16:9 clips at one low flat price.
View modelWan 2.6
Short vertical or wide clips with sound, on a budget.
View modelByteDance Video Upscaler
Restoring low-resolution source in the middle of a pipeline.
View modelImage models
Conversational editing, photoreal finals, and print-resolution output. Draft on a flash tier, finish on a flagship.
Gemini 2.5 Flash Image
Fast conversational edits and consistent characters.
View modelGemini 3.1 Flash Image
New projects wanting the latest fast Google image model.
View modelNano Banana Pro
Finals at up to 4K from many references.
View modelFLUX.2 Pro
Hero assets and designs where the text must read.
View modelSeedream 4.5
Print-resolution assets and multi-reference composition.
View modelSeedream 5.0
Lifelike commercial stills and precise edits.
View modelRecraft V4.1
Polished images, drafted on Flash and finished on Pro.
View modelGPT Image 2
Precise photo edits and legible text in frame.
View modelQwen Image 3
Menus, labels, and infographics with small print.
View modelQwen Image 2.1
Fast generation and edits, with a cheaper Turbo tier.
View modelFLUX.3 Image
Multi-reference edits and compositions.
View modelFLUX 3 Image Klein
Fast drafts, batches, and consistent sets.
View modelSeedream 5.0 Flash
High-volume product shots and variations.
View modelHy Image 3.5 Preview
Multi-reference product and character composites.
View modelNano Banana 2.1
Fast product and character edits with references.
View modelGrok Imagine Image 2.0
Fast, low-cost stills and quick reference edits.
View modelMAI-Image-2.6
Design-ready stills, drafted on Flash.
View modelMuse Image
Multi-part briefs and quick reference edits.
View modelKrea 2
Textured stills and fast design exploration.
View modelRiverflow 2.5
Reference-driven product finals, drafted on Fast.
View modelAlso on the canvas
Language and speech models power the prompting and narration stages of a pipeline. And any Hugging Face or OpenRouter model id can be typed straight into a node.
Language
Drafting, rewriting, classification, and reasoning, from frontier models to open weights.
- Claude Sonnet 5
- GPT-5
- Gemini 3.1 Pro
- Llama 3.3 70B
- DeepSeek R1
- Qwen2.5 72B
- Mixtral 8x22B
Speech & audio
Voiceovers, narration, music, sound effects, and transcription.
- ElevenLabs v3
- ElevenLabs Multilingual v2
- Lyria 3 Pro
- Whisper Large v3
- HEKokoro 82M
- Voxtral Mini TTS
- Gemini Flash TTS
- ElevenLabs SFX
Your first video is one prompt away.
Generate your first video, image, or draft today. Prepaid credits, no subscription.