Stability AI: Stable Diffusion 3.5 Large Turbo

Stable Diffusion 3.5 Large Turbo is the accelerated variant of the Large image model. It is useful for generating multiple concept directions with fewer sampling steps while retaining the Large family's visual foundation.

Compare models

sd3.5-large-turbo

AvailableStability AIImageSync

Price: From $0.04
Modalities: Image

About Stable Diffusion 3.5 Large Turbo

Stable Diffusion 3.5 Large Turbo is a distilled version of Stable Diffusion 3.5 Large from Stability AI. Stability states it generates images in four steps, which makes it much quicker to run than the full model while keeping the same visual foundation. It fits generating several concept directions in a row. When the last bit of prompt accuracy matters, the non-turbo Large is the better choice.

Where it works well

Four-step sampling, per Stability, makes each generation noticeably faster than the full Large model.
Keeps the Large family's visual foundation, so style and subject range resemble Large.
Quick enough to test many prompt variants in one sitting.

When to choose another model

Stability gives the full Large model the lead on prompt accuracy.
As a distilled model, it may offer less room for fine control through sampling settings.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to imageTokenLab endpoint

POST/v1/images/generations

curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "operation": "text-to-image",
  "model": "sd3.5-large-turbo",
  "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
}'

Parameters

Text to image

Parameter	Values and limits	Default	Notes
`aspect_ratio`	Not provided	Not provided	Model-specific aspect-ratio values and the default are not yet verified for this public operation.
`model`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided

Follows the official Stability SD3.5 Large Turbo contract.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Text to image

per image

Official price: $0.04
Verified price: —
Discount: —

	Official priceper image	Verified priceper image	Discount
Text to image	$0.04	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 8:35 PM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Stable Diffusion 3.5 Large Turbo in Console with a prompt ready to edit or send.

Help me create an image with sd3.5-large-turbo using text-to-image at /v1/images/generations. Show the result, cost, and any limits I should know.

Use cases

Best for

Text to Image

Concept sweeps
Generate a batch of directions for one idea and shortlist the best.
Live previews
Return images fast enough for an interactive design tool, where the user types a prompt and expects a picture within moments.
Deck and mood-board imagery
Produce quick reference pictures for presentations and mood boards, discarding weak results cheaply and keeping the few that fit.
Two-stage workflow
Draft with Turbo, then re-run chosen prompts on Large for the final.

Prompt examples

Five different logo concepts for a bakery called Ember, flat vector, warm colours.

A foggy harbor at dawn with fishing boats, soft muted tones.

Robot librarian in a vast circular library, cinematic lighting.

FAQ

What is SD 3.5 Large Turbo?

A distilled variant of Stable Diffusion 3.5 Large, built by Stability AI to produce images in just four steps, so that generation is much faster than with the full Large model.

Is it as good as Large?

Stability describes it as prioritising speed while maintaining quality, and credits Large with the best prompt accuracy. Test your own prompts to see the gap.

When should I pick Turbo over Medium?

Pick Turbo for Large-style output at speed. Medium is a smaller 2.5 billion parameter model built to run on consumer hardware, and it supports a wider range of output sizes than the Large family.

Does Large Turbo take image input?

No. This listing is text-to-image, so it works from the prompt alone. If you need to edit or restyle an existing image, use Stability's Control, Style Guide, or Inpaint services, which accept an image as well.

Is Large Turbo the same as sd3.5-flash?

No. Flash is a separate listing described in the catalog as an option for quick exploration, while Large Turbo is Stability's documented four-step distilled version of the Large model. Compare both on your own prompts.

How much does Stable Diffusion 3.5 Large Turbo cost?

On TokenLab, Stable Diffusion 3.5 Large Turbo costs $0.04 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Stable Diffusion 3.5 Large Turbo use?

Use https://api.tokenlab.sh/v1/images/generations for Stable Diffusion 3.5 Large Turbo. The request example below shows the matching code shape.

Which operations does Stable Diffusion 3.5 Large Turbo support?

Stable Diffusion 3.5 Large Turbo supports Text to image. Select an operation above to see its endpoint and request example.