3D models

3D models

Anyone who needs a standalone 3D asset — a product mockup, a prop or character mesh for episodic animation, a piece for a scene — without opening 3D software.

What you get

  • A 3D model generated from a prompt or a reference image, in a format ready to preview and reuse
  • A preview you look at before deciding what happens next — nothing downstream runs until you choose it
  • An optional, off-by-default step to place the model into a scene at a size you set, instead of a second manual import

Generating a model and placing it in a scene are two separate steps, so you can generate, look, and decide — never a surprise auto-import into the wrong project

A placed model is sized and centred predictably rather than landing at whatever scale it happened to generate at

This is stated honestly rather than as a live path: 3D generation is specified and registered as its own service, but the generation pipeline behind it isn't running yet — nothing here can be submitted until it is.

Settings you control

Every setting below ships with a real default — never a blank. Nothing here is asked unless it’s something the agent genuinely can’t infer, or changes the output or the price.

mode

Default: text-to-3d

Inferred from whether a reference image is attached

quality
Affects price

Default: standard

Never asked — standard unless you choose fast

autoPlaceInScene

Default: false

Never asked — explicit opt-in, off by default

placementTargetSizeMeters

Default: 1m

Never asked unless autoPlaceInScene is on

Pricing

Priced per finished piece from your live plan — see the exact, itemised quote in Preview before anything spends. Nothing here is a static number; it's computed from your settings every time.

See a preview

Models this service can use

The model roster for this service is being finalised — see the full, current lineup on the models page.

Where it publishes

Every plan reaches every platform below — tiers gate how many connections you get, never which platforms you can reach.

SNW
See all platforms

What runs unattended vs. needs your approval

This is the target procedure, stated honestly rather than as a live path: a run would generate the model from your prompt or reference image at the chosen quality, hold it for your preview, and — only if you've turned autoPlaceInScene on — place it into the target scene at the size you set. Nothing here runs yet: the generation pipeline behind this service isn't live, so no job can be submitted or spent against it today.

Auto-post is off by default. A new workspace approves its first five pieces one at a time before anything publishes unattended.

Auto-publishing without approval is a Pro-plan-and-up feature — a risk gate, not a cost one. Producing a piece costs the same whoever ordered it; posting to your real account unattended is a different exposure.

Reference: recommended. A reference image is required only when mode is image-to-3d; a text description alone is enough for text-to-3d.

Sample outputs

Frequently asked

Is this live yet?

Not yet — the service is fully specified and registered, but the generation pipeline behind it isn't running. It shows here as not yet available rather than as a button that would fail if you pressed it.

Do I need to provide a reference?

Only for image-to-3d — give it a reference image and it builds from that. Otherwise, a text description is enough.

Does generating a model also put it in a scene?

No, not unless you turn autoPlaceInScene on. The default is to generate and preview only; placing it into a scene is a separate, explicit step.

Does pricing depend on the quality I pick?

Yes — quality is priced per generation and quoted before anything spends, same as every other service here; it's never a flat number baked into the page.

Related services