Stability AI: Stable Diffusion 3.5 Medium

Stable Diffusion 3.5 Medium 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-medium

AvailableStability AIImageSync

Price: From $0.035
Modalities: Image

About Stable Diffusion 3.5 Medium

Stable Diffusion 3.5 Medium is the smallest of the three SD 3.5 releases from Stability AI, at 2.5 billion parameters. Stability built it to run out of the box on consumer hardware and to support images from 0.25 to 2 megapixels. It trades some peak quality for efficiency, sitting below Large in prompt accuracy but with a wider range of output sizes.

Where it works well

Stability's description stresses resource efficiency alongside better image quality, typography, and complex prompt understanding.
Supports a wider range of output sizes, from 0.25 to 2 megapixels, than the one-megapixel Large.
Shares the MMDiT-X design and prompt adherence goals of the larger SD 3.5 models.

When to choose another model

Stability presents Large as the leader in prompt accuracy.
Greater seed variation, which Stability intentionally allows, makes vague prompts less predictable.

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-medium",
  "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 Medium 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: $0.035
Verified price: —
Discount: —

	Official priceper image	Verified priceper image	Discount
Text to image	$0.035	—	—

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, 2:02 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 Medium in Console with a prompt ready to edit or send.

Help me create an image with sd3.5-medium 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

Larger-format graphics
Create wallpapers or banners where a bigger canvas is needed than the typical one megapixel.
Cost-aware generation
Fill content libraries and template galleries with many images when you want a compact, efficient model rather than the largest one.
Local-to-cloud parity
Match results from a team that runs the open Medium weights on its own machines, so prototypes made locally can move to an API unchanged.
Everyday illustration
Produce blog, newsletter, and social images from clear prompts where moderate detail is enough and turnaround matters for the schedule.

Prompt examples

Wide panoramic banner of a misty bamboo forest at sunrise, soft pastel tones.

A children's book illustration of a badger baking bread in a burrow.

Product mockup of a canvas tote bag on a wooden bench, natural light.

FAQ

What is SD 3.5 Medium?

A 2.5 billion parameter text-to-image model from Stability AI, the compact member of the Stable Diffusion 3.5 family, designed to run out of the box on consumer hardware while still following prompts well.

What image sizes does SD 3.5 Medium support?

Stability states support for 0.25 to 2 megapixels, which is a wider range than the one-megapixel focus of Large. That makes it a reasonable pick when you need small thumbnails and larger banners from one model.

Why choose Medium over Large?

Choose Medium for efficiency and larger formats. Choose Large when prompt accuracy and quality matter most, since Stability describes Large as the most capable of the three SD 3.5 releases for professional work.

Does Medium accept reference images?

No, it is text-to-image only. Use Stability's Control, Style Guide, or Inpaint services when you want a reference picture to guide or change the result, since those accept an image together with a prompt.

How much does Stable Diffusion 3.5 Medium cost?

On TokenLab, Stable Diffusion 3.5 Medium costs $0.035 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 Medium use?

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

Which operations does Stable Diffusion 3.5 Medium support?

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