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.

Google

Veo 3.1

Google

Cinematic hero shots with synced dialogue and sound.

View model
Google

Veo 3.1 Fast

Google

Fast drafts, prompt exploration, and batch social clips.

View model
Google

Veo 3.1 Lite

Google

Affordable Veo clips with audio, at volume.

View model
Kling

Kling 3.0 Pro

Kuaishou

Dance, sport, and action with consistent characters.

View model
ByteDance

Seedance 2.0

ByteDance

Consistent products and characters across whole campaigns.

View model
ByteDance

Seedance 2.5

ByteDance

Long single-take clips and daily short-form volume.

View model
ByteDance

Seedance 1.5 Pro

ByteDance

Low-cost reference-driven clips and silent drafts.

View model
Grok

Grok Imagine

xAI

High-volume drafts, memes, and clips from real photos.

View model
Grok

Grok Imagine 1.5

xAI

Grok Imagine ideas finished at up to 1080p.

View model
Grok

Grok Imagine 1.5 Lite

xAI

Cheap, fast drafts of Grok Imagine ideas.

View model
HE

HeyGen Video

HeyGen

Fast, low-cost drafts, variations, and social clips.

View model
ByteDance

Seedance 2.0 Fast

ByteDance

Seedance 2.0 quality for drafts and volume work.

View model
ByteDance

Seedance 2.0 Mini

ByteDance

Hook tests, storyboards, and high-volume drafts.

View model
MI

Hailuo 3 Max

MiniMax

Quick clips that start and land on your frames.

View model
Alibaba

Wan 2.7

Alibaba

People-led clips built from real photos.

View model
Alibaba

Wan 3.0

Alibaba

Long single takes, from 2 to 30 seconds.

View model
Alibaba

HappyHorse 1.1

Alibaba

Reference-driven clips up to 15 seconds in seven formats.

View model
MI

Hailuo 3

MiniMax

Controlled prompts and legible brand text.

View model
RU

Runway Gen-4.5

Runway

Cinematic shot craft with reproducible iteration.

View model
Flux

FLUX.3 Video

Black Forest Labs

Long takes, keyframe control, and extending footage.

View model
Kling

Kling Video O1

Kuaishou

Everyday clips and scheduled pipelines on a budget.

View model
Kling

Kling 3.0 Standard

Kuaishou

Kling motion for drafts and volume, at half the Pro price.

View model
MI

Hailuo 2.3

MiniMax

Silent 16:9 clips at one low flat price.

View model
Alibaba

Wan 2.6

Alibaba

Short vertical or wide clips with sound, on a budget.

View model
ByteDance

ByteDance Video Upscaler

ByteDance

Restoring low-resolution source in the middle of a pipeline.

View model

Image models

Conversational editing, photoreal finals, and print-resolution output. Draft on a flash tier, finish on a flagship.

Gemini

Gemini 2.5 Flash Image

Google

Fast conversational edits and consistent characters.

View model
Gemini

Gemini 3.1 Flash Image

Google

New projects wanting the latest fast Google image model.

View model
Gemini

Nano Banana Pro

Google

Finals at up to 4K from many references.

View model
Flux

FLUX.2 Pro

Black Forest Labs

Hero assets and designs where the text must read.

View model
ByteDance

Seedream 4.5

ByteDance

Print-resolution assets and multi-reference composition.

View model
ByteDance

Seedream 5.0

ByteDance

Lifelike commercial stills and precise edits.

View model
RE

Recraft V4.1

Recraft

Polished images, drafted on Flash and finished on Pro.

View model
OpenAI

GPT Image 2

OpenAI

Precise photo edits and legible text in frame.

View model
Qwen

Qwen Image 3

Qwen

Menus, labels, and infographics with small print.

View model
Qwen

Qwen Image 2.1

Qwen

Fast generation and edits, with a cheaper Turbo tier.

View model
Flux

FLUX.3 Image

Black Forest Labs

Multi-reference edits and compositions.

View model
Flux

FLUX 3 Image Klein

Black Forest Labs

Fast drafts, batches, and consistent sets.

View model
ByteDance

Seedream 5.0 Flash

ByteDance

High-volume product shots and variations.

View model
TE

Hy Image 3.5 Preview

Tencent

Multi-reference product and character composites.

View model
Gemini

Nano Banana 2.1

Google

Fast product and character edits with references.

View model
Grok

Grok Imagine Image 2.0

xAI

Fast, low-cost stills and quick reference edits.

View model
Azure

MAI-Image-2.6

Microsoft

Design-ready stills, drafted on Flash.

View model
Meta

Muse Image

Meta

Multi-part briefs and quick reference edits.

View model
KR

Krea 2

Krea

Textured stills and fast design exploration.

View model
SO

Riverflow 2.5

Sourceful

Reference-driven product finals, drafted on Fast.

View model

Also 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.

  • AnthropicClaude Sonnet 5
  • OpenAIGPT-5
  • GeminiGemini 3.1 Pro
  • MetaLlama 3.3 70B
  • DeepSeekDeepSeek R1
  • QwenQwen2.5 72B
  • MistralMixtral 8x22B

Speech & audio

Voiceovers, narration, music, sound effects, and transcription.

  • ElevenLabs v3
  • ElevenLabs Multilingual v2
  • GoogleLyria 3 Pro
  • OpenAIWhisper Large v3
  • HEKokoro 82M
  • MistralVoxtral Mini TTS
  • GeminiGemini Flash TTS
  • ElevenLabs SFX