The node editor for
generative media.
Build AI image workflows with models, tools, data, and security built in.
The best generative models, on one canvas
Pick a model per node and swap it any time, with no rewrites and no lock-in. New models drop in the day they’re released.
Video
Cinematic clips from a prompt — duration, aspect ratio, and audio per model.
Image
Product shots, illustrations, and campaign art — resolution and aspect per model.
Language
Drafting, rewriting, classification, and reasoning with open-weight models.
Speech & audio
Voiceovers, narration, transcription, and embeddings for search and retrieval.
Veo 3.1
Video
Veo 3.1 Fast
Video
Sora 2 Pro
Video
Kling 3.0 Pro
Video
Seedance 2.0
Video
Grok Imagine
Video
Wan 2.7
Video
Gemini 2.5 Flash Image
Image
Gemini 3.1 Flash Image
Image
FLUX.2 Pro
Image
Seedream 4.5
Image
Llama 3.3 70B
Language
DeepSeek R1
Language
Qwen2.5 72B
Language
Mixtral 8x22B
Language
Kokoro 82M
Speech & audio
Voxtral Mini TTS
Speech & audio
Gemini Flash TTS
Speech & audio
Whisper Large v3
Speech & audio
BGE Large EN
Speech & audio
Not listed? Type any open model id straight into the node, whether a Hugging Face repo or an OpenRouter model.
Everything you need to build and ship AI
Everything behind the prompt: models, pipelines, and APIs, built to ship, not just to demo.
Visual pipeline builder
Wire open-source models, guardrails, and integrations into a pipeline on a drag-and-drop canvas. No glue code between the pieces.
Learn moreOne API, two ways to call it
Every pipeline gets a versioned endpoint. Use the typed /invoke API or an OpenAI-compatible /chat/completions endpoint. Point any OpenAI SDK at it, streaming included.
Learn moreEvery modality, one canvas
Pick a model per node: Together, OpenRouter, Fireworks, DeepSeek, and more via an OpenAI-compatible backend. Swap models per node, never locked to one provider.
Learn moreGuardrails when you want them
Drop redaction, PII guardrail, and conditional routing nodes into any pipeline so sensitive data is handled before it reaches a model or external system.
Learn moreVersioning & run history
Version and roll back any pipeline. Every run is logged with per-node timing, tokens, and success rate. Export the trail for SOC 2, HIPAA, or your next audit.
Learn moreProduction-ready
Automatic retries and fallback models, a KMS-encrypted secrets manager, and hardware-attested Treza Enclaves on Enterprise, with provable evidence the right code handled your data.
Learn moreBuilt by people from
We've built pipelines, infrastructure, and platforms at global scale.
Common questions
What people ask before their first generation.
What can I generate with Treza?
Video with Veo 3.1 and Sora 2, images with Gemini image models, and text with open models like Llama, DeepSeek, and Qwen, plus transcription and embeddings. Each generator is a node on a canvas, so one prompt can drive several modalities in a single pipeline.
How is this different from a single AI generator?
A one-shot generator gives you one output from one model. Treza runs the whole workflow: one node can refine your brief into a proper shot prompt, the next renders the video, another drafts the caption. Then the entire pipeline publishes as an API you can call from your product.
Which models can I use?
The catalog covers the major open families (Llama, Mistral, Qwen, DeepSeek, Gemma, Phi) alongside Veo, Sora, and Gemini image models for media. Not listed? Type any Hugging Face or OpenRouter model id straight into the node. Swap models per node, never locked to one provider.
Do I have to rewrite my code?
No. Every pipeline exposes an OpenAI-compatible /chat/completions endpoint, streaming included. Point any OpenAI SDK at it: change the base URL and API key and you’re done. Prefer a native integration? Call the typed /invoke endpoint, with JSON inputs and outputs derived from the graph.
Can I see what each generation did?
Yes. Every run is logged with per-node timing, tokens, and success rate, so you can see exactly how a prompt became an output. Version and roll back any pipeline, and export run history any time.
How much does it cost?
There's no subscription. You buy prepaid credits (starting at $10) and spend them as you run models, with only successful runs charged. New accounts start with $5 in free credits, and credits never expire. Enterprise adds dedicated enclaves, SSO, postpaid invoicing, and custom contracts.
Your next prompt could be production.
Generate your first video, image, or draft today. Start with $5 in free credits — no card, no subscription.