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 modelSora 2 Pro
Story-length clips with dialogue and a beginning, middle, end.
View modelKling 3.0 Pro
Dance, sport, and action with consistent characters.
View modelSeedance 2.0
Consistent products and characters across whole campaigns.
View modelGrok Imagine
High-volume drafts, memes, and clips from real photos.
View modelWan 2.7
People-led clips built from real photos.
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 modelFLUX.2 Pro
Hero assets and designs where the text must read.
View modelSeedream 4.5
Print-resolution assets and multi-reference composition.
View modelAlso on the canvas
Language, speech, and embedding models power the prompting, narration, and search 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 with open-weight models.
- Llama 3.3 70B
- DeepSeek R1
- Qwen2.5 72B
- Mixtral 8x22B
Speech & audio
Voiceovers, narration, transcription, and embeddings for search and retrieval.
- HEKokoro 82M
- Voxtral Mini TTS
- Gemini Flash TTS
- Whisper Large v3
- BGBGE Large EN
Your next prompt could be production.
Generate your first video, image, or draft today. Prepaid credits, no subscription.