Models
Every generation node in a pipeline runs a model. Treza reaches models through an OpenAI-compatible backend that spans providers like Together, OpenRouter, Fireworks, and DeepSeek, so you can pick the best model for each step and never get locked into one vendor.
The catalog
The catalog covers every modality. Pick a model per node from the lists below, or type any model id straight in (see Any model id).
Video
Cinematic clips from a sentence, with duration and aspect ratio set per node.
Seedance 2.5
Seedance 2.0
Veo 3.1
Veo 3.1 Fast
Kling 3.0 Pro
Wan 2.6
Image
Product shots, illustrations, and campaign art with full response metadata.
Gemini 2.5 Flash Image
Gemini 3 Pro Image
Language
Drafting, rewriting, classification, and reasoning with open-weight models.
Llama 3.3 70B
DeepSeek R1
Qwen2.5 72B
Mixtral 8x22B
The catalog also covers the major open families: Llama, Mistral, Qwen, DeepSeek, Gemma, and Phi, plus hosted Claude and GPT models.
Reasoning
Some hosted models can think before they answer. On a Text Generation node this is a per-node Reasoning setting: Off, Low, Medium, or High. Off is the default and the right choice for prompt-driven steps such as picking a clip, rewriting copy, or classifying, where the instructions already carry the rules. Turn it up for a node that has to weigh data it is given. Thinking is billed as output tokens; when reasoning is on, the node raises its request cap so the reply still fits inside Max tokens. Models without reasoning ignore the setting.
Audio & embeddings
Transcribe speech and vectorize text for search and retrieval steps.
Whisper Large v3
BGE Large EN
Any model id
Not listed? Type any Hugging Face or OpenRouter model id directly into the node and Treza will route to it through the OpenAI-compatible backend. This means new models are usable the day they ship, without waiting for them to be added to the catalog.
Swap models, no lock-in
One model per node, changeable at any time. Swapping a model never requires rewriting the rest of the pipeline.
Per-node choice. Use a fast, cheap model to refine a brief and a premium model to render the final asset.
Bring your own keys. Store provider API keys in the encrypted secrets manager. Keys are used server-side and never returned by any API, so you are never tied to one price or one vendor.
Cost
Model runs are paid for with prepaid credits. A failed generation costs nothing; if a run stops partway, the steps that finished are charged. There is no subscription: you buy credits once and spend them as you run models. Every run records its token counts and cost in run history. See Plans & Pricing.
Last updated