Stability AI: Stable Diffusion 3.5 Large

Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Compare models

sd3.5-large

AvailableStability AIImageSync

Price: From $0.065
Modalities: Image

About Stable Diffusion 3.5 Large

Stable Diffusion 3.5 Large is the largest Stability AI model in the SD 3.5 family, a Multimodal Diffusion Transformer text-to-image model with 8.1 billion parameters. Stability positions it for professional work at around one megapixel, with the strongest prompt adherence of the three SD 3.5 releases. Large Turbo is its four-step distilled sibling, and Medium is a smaller model.

Where it works well

Stability describes it as the most capable of the SD 3.5 models, with leading prompt adherence.
Natural at about one megapixel, a size that fits web and illustration use.
Built for improved image quality, typography, and complex-prompt understanding.

When to choose another model

It is slower than Large Turbo, which needs only four steps.
Stability says output varies more across seeds, so under-specified prompts can give uncertain results.

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",
  "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 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: $0.065
Verified price: —
Discount: —

	Official priceper image	Verified priceper image	Discount
Text to image	$0.065	—	—

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, 8:02 AM 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 in Console with a prompt ready to edit or send.

Help me create an image with sd3.5-large 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

Professional illustration
Generate polished artwork from detailed prompts with several subjects and a stated style.
Marketing visuals
Produce campaign images from detailed briefs where prompt adherence matters, such as a product, a setting, and a named colour palette in one scene.
Typography-led designs
Try posters and signage where words appear in the image, checking spelling each time.
Baseline for comparison
Use it as the quality reference when testing faster or smaller models, so you can see what a lighter option gives up on your own prompts.

Prompt examples

A vintage travel poster for a lighthouse coast, bold lettering reading 'Cape Hollow', art deco style.

Two astronauts playing chess on a red desert hill, golden hour, painterly.

Overhead view of a laid-out breakfast on a blue table, soft daylight, natural colours.

FAQ

What is SD 3.5 Large?

An 8.1 billion parameter MMDiT-X text-to-image model from Stability AI, the quality-first member of the Stable Diffusion 3.5 family, aimed at professional work at around one megapixel.

How does Large differ from Large Turbo?

Large Turbo is a distilled version that generates in four steps for speed. Large is the original, aiming for higher prompt accuracy at the cost of slower sampling.

How does it differ from Medium?

Medium has 2.5 billion parameters and was built to run on consumer hardware at 0.25 to 2 megapixels. Large targets professional quality at roughly one megapixel.

Does SD 3.5 Large vary between seeds?

Yes. Stability states it deliberately allows greater variation across seeds to preserve diverse styles, so be specific in prompts when you need repeatable outputs, and expect vague prompts to produce a wider spread of results.

Is Large better than Medium for typography?

Large is credited by Stability with the strongest prompt accuracy of the three SD 3.5 models, which helps with prompts that specify exact words. Spell-check any lettering in the output, since diffusion models can still slip on text.

How much does Stable Diffusion 3.5 Large cost?

On TokenLab, Stable Diffusion 3.5 Large costs $0.065 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 use?

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

Which operations does Stable Diffusion 3.5 Large support?

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