HeyGen Video. Fast, low-cost clips from a prompt, a frame, or references.
HeyGen's general-purpose video model. Five to fifteen second clips at 480p or 768p in six aspect ratios, started from text, an exact first frame, or reference images, at one of the lowest per-second prices of any video model on Treza.
- 5 to 15 second clips
- 6 aspect ratios
- First frame control
- Reference images
- 480p or 768p
HeyGen Video is HeyGen's general-purpose video model, released on OpenRouter at the end of September 2026. It turns a text prompt, an exact first frame, or a set of reference images into a clip of 5 to 15 seconds at 480p or 768p, in six aspect ratios from 21:9 widescreen to 9:16 vertical. It is built for speed and price rather than resolution: in our launch-week tests, five second clips came back in under 20 seconds.
On Treza it sits in the Video Generation node's picker and in chat. Leave Resolution on Model default and it renders 768p, or pick 480p for the cheapest drafts. Wire reference images into the node to carry a product or a character into a new scene, then chain the clip into captions, narration, and publishing like any other step. It bills from prepaid credits, and only successful runs are charged.
Fast turnaround
Five second clips came back in under 20 seconds in our launch-week tests, quick enough to iterate on a prompt in the time a slower model renders once.
Low cost per second
One of the lowest per-second prices of any video model on Treza, so drafts, variations, and high-volume social clips stay cheap. 480p costs less than 768p.
Frames and references
Open on an exact first frame, or wire reference images into the node to keep a product or character recognizable in a scene it was never photographed in.
Six aspect ratios
21:9, 16:9, 4:3, 1:1, 3:4, and 9:16, from cinematic widescreen to vertical Shorts, at any whole second from 5 to 15.
What to make with HeyGen Video
Real prompts, and what comes back. Every one runs in Treza chat or as a node on the canvas.
“A barista pours steamed milk into a latte in a sunlit cafe, slow push-in, 9:16”
A vertical cafe beat, back in seconds.
“Start on this product photo (attached): a shaft of morning sun drifts slowly across it”
Image-to-video from your exact opening frame.
“Use these photos of our sneaker as references: it sits on a wet street at night, neon reflections, 16:9”
The same product carried into a new scene.
“Eight variations of a 5 second hook for an ad test, 480p”
Cheap drafts to pick a winner from.
“A 15 second pass over a misty pine forest at dawn, 21:9”
A long cinematic establishing shot.
“A 1:1 loop of a ceramic mug steaming on a windowsill”
A square clip sized for product feeds.
HeyGen Video is one node on a canvas
Chain it with language, image, and video models, then publish the whole pipeline as an API. See how a full AI video pipeline fits together.
- Step 01
Draft the brief
A language model node expands a one-line idea into a detailed, on-brand prompt before it ever reaches the model.
- Step 02
Generate with HeyGen Video
Run variants in parallel, compare against other models on the same prompt, and keep every result in run history.
- Step 03
Publish it as an API
The pipeline becomes a versioned endpoint. Your product calls it with the typed /invoke API or any OpenAI SDK.
HeyGen Video as an API, priced per clip
The HeyGen Video API
Build a pipeline with HeyGen Video on a node and publish it. It becomes a versioned HTTP endpoint: the typed /invoke route enqueues a run and returns a run id to poll, and an OpenAI-compatible route works with SDKs you already use. Agents connect over MCP the same way. Your prompt engineering ships inside the pipeline, so every caller gets your quality, and swapping the model later does not change the API your product calls.
HeyGen Video pricing
Prepaid credits, no subscription. Each clip is charged at HeyGen Video's own rate from your balance, shown before you run, and only successful generations are charged, so a failed run costs nothing. Credit packs start at $5 and never expire, which suits spiky production schedules. Run history records the cost of every generation, per node, so spend is auditable rather than a surprise.
HeyGen Video, answered
Is HeyGen Video the same as HeyGen's avatars?
No. HeyGen Video is HeyGen's general-purpose generator for scenes, products, and motion. HeyGen's photo-to-talking-head model, Avatar IV, is a separate model that the Video Generation node does not run. For a talking head on Treza, pair a clip with the Lipsync node.
What resolution does HeyGen Video render?
480p or 768p, picked with the Video Generation node's Resolution setting. Left on Model default it renders 768p. A clip made from reference images costs more per second than one made from a prompt or a first frame, at either resolution.
Does HeyGen Video generate audio?
Clips come back with a faint ambient track and no setting to change it, so treat them as picture. For sound that carries the clip, add a Text to Speech or Audio Generation node and mix it in with the Sequence node.
How much does HeyGen Video cost on Treza?
Treza uses prepaid credits with no subscription. Each clip is charged at HeyGen Video's rate from your balance, and only successful generations are charged. Credit packs start at $5 and never expire.
Can I call HeyGen Video through an API?
Yes. Build a pipeline that uses HeyGen Video and publish it as a versioned HTTP endpoint. Call the typed /invoke API from your product, or point any OpenAI SDK at the OpenAI-compatible endpoint. If a better model ships later, swap it on the node without changing the API your product calls.
Your first video is one prompt away.
Generate your first video, image, or draft today. Prepaid credits, no subscription.