Stability AI: Stable Diffusion 3.5 Flash

Stable Diffusion 3.5 Flash is a prompt-to-image option for quick visual exploration. It is suited to trying scene ideas and composition alternatives before choosing which concept deserves further refinement.

Compare models

sd3.5-flash

AvailableStability AIImageSync

Price: From $0.025
Modalities: Image

About Stable Diffusion 3.5 Flash

Stable Diffusion 3.5 Flash is a Stability AI text-to-image model offered for quick visual exploration. It turns a prompt into an image so you can test scene ideas and composition alternatives, then pick which concept deserves a slower pass. Within the SD 3.5 family it is the speed-oriented entry, with Large for quality and Large Turbo and Medium in between.

Where it works well

Aimed at fast iteration, so many composition ideas can be tried per session.
Text-only input keeps integration simple.
Part of the SD 3.5 line, so prompts written for its siblings carry over as a starting point.

When to choose another model

It takes text only, with no image input for guiding or editing.
For final artwork, sd3.5-large or Stable Image Ultra is the safer pick.

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-flash",
  "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 Flash 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: $0.025
Verified price: —
Discount: —

	Official priceper image	Verified priceper image	Discount
Text to image	$0.025	—	—

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, 8:12 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 Flash in Console with a prompt ready to edit or send.

Help me create an image with sd3.5-flash 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

Prompt testing
Run many phrasings of one idea to see which direction works before spending on higher-quality runs.
Layout brainstorming
Explore framing, camera angle, and scene alternatives for storyboards and thumbnails before choosing which composition deserves a slower, higher-quality render.
Mood boards
Gather quick visual references of style, palette, and subject for a pitch, then keep the strongest frames and discard the rest without much cost.
Interactive tools
Power apps where the user waits for each preview, such as prompt playgrounds, where short turnaround matters more than the last increment of detail.

Prompt examples

Three variations of a cosy mountain cabin in winter, different camera angles.

A cyberpunk market alley at night, neon signs, wet pavement, wide shot.

A minimalist logo-style sketch of a paper plane, flat colours.

FAQ

What is the sd3.5-flash model?

A Stable Diffusion 3.5 text-to-image option from Stability AI, suited to quick exploration of prompts, scene ideas, and composition alternatives before one concept is refined further.

How does it differ from sd3.5-large-turbo?

Both favour speed, but Large Turbo is described by Stability as a distilled Large model that works in four steps. Flash is positioned for exploration, so compare outputs side by side on one prompt.

Is Flash good for final images?

It is suited to drafts and exploration. Move promising prompts to sd3.5-large or Stable Image Ultra for polished results, since Stability's own pages describe Large as the quality-first member of the SD 3.5 family.

Does Flash accept an input image?

No, it is text-to-image only. For editing or guiding with an existing picture, use one of Stability's image services such as Inpaint, Control Structure, or Style Guide, which take an image along with the prompt.

What prompts suit Flash?

Short, concrete prompts that name a subject, a setting, and a camera angle work well for exploration. Generate several variations, then carry the best wording to Large or Stable Image Ultra for the final render.

How much does Stable Diffusion 3.5 Flash cost?

On TokenLab, Stable Diffusion 3.5 Flash costs $0.025 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 Flash use?

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

Which operations does Stable Diffusion 3.5 Flash support?

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