Start building

Stable Cascade

stability-ai/stable-cascade

Stable Cascade by Stability AI - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.

Use in agentGet API key
Base price
$0.0006 / run
Execution
async
Model type
image
Input fields
7

Try the model

Playground

Open playground
Input
The prompt to use for generating the image. Be as descriptive as possible for best results.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
020
The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. Range: 0 to 20.
The same seed and the same prompt given to the same version of Stable Cascade will output the same image every time.
440
Number of steps to run the first stage for. Range: 4 to 40.
020
The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. Range: 0 to 20.
424
Number of steps to run the second stage for. Range: 4 to 24.
OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price
$0.0006 / run

Context & modalities

Input
Schema-defined
Output
image

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
Stability AI
Model ID
stability-ai/stable-cascade
Execution
async
API
Unified Run API
Endpoint
/v1/run

API README

Stable Cascade

Stable Cascade occupies a clearly bounded position in a image production pipeline under the route stability-ai/stable-cascade. It is best evaluated as a named workflow endpoint rather than as a generic substitute for neighboring versions: planners can assign the route to a specific brief, record the chosen revision, and keep approval history tied to one predictable integration surface from intake through delivery.

A practical rollout of Stable Cascade should begin with source-readiness checks, ownership of the submitted material, an agreed budget, and a written definition of the final stable cascade deliverable. Before automation is enabled, the acceptance pass should verify that the returned asset opens correctly, fits the intended downstream toolchain, satisfies the project’s review criteria, and can be reproduced from the stored request and route identity stability-ai/stable-cascade.

Highlights

  • Distinct output behavior. For Stable Cascade, for Stable Cascade, set the opening stage between 4 and 40 steps In Stable Cascade, this capability is applied through the exact stability-ai/stable-cascade workflow with seed as a relevant request control; the seed control exposes the corresponding choice in this route; the seed control exposes the corresponding choice in this route.
  • Creative control. For Stable Cascade, for Stable Cascade, allocate 4–24 steps to the second stage In Stable Cascade, this capability is applied through the exact stability-ai/stable-cascade workflow with prompt as a relevant request control; the prompt control exposes the corresponding choice in this route; the prompt control exposes the corresponding choice in this route.
  • Workflow fit. For Stable Cascade, for Stable Cascade, tune general guidance and second-stage guidance independently In Stable Cascade, this capability is applied through the exact stability-ai/stable-cascade workflow with aspect ratio as a relevant request control; the aspect ratio control exposes the corresponding choice in this route; the aspect ratio control exposes the corresponding choice in this route.
  • Production detail. For Stable Cascade, for Stable Cascade, choose one of ten aspect ratios for the generated image In Stable Cascade, this capability is applied through the exact stability-ai/stable-cascade workflow with guidance scale as a relevant request control; the guidance scale control exposes the corresponding choice in this route; the guidance scale control exposes the corresponding choice in this route.

Pricing

ConfigurationPrice
Per request$0.000575

When to Use

ScenarioWhy this model fits
Choose Stable CascadeUse it when the required deliverable is specifically the image result documented for stability-ai/stable-cascade.
Match the source materialSelect this route when your inputs naturally map to seed, prompt, aspect_ratio, guidance_scale.
Use its distinguishing capabilityFor Stable Cascade, set the opening stage between 4 and 40 steps In Stable Cascade, this capability is applied through the exact stability-ai/stable-cascade workflow with seed as a relevant request control; the seed control exposes the corresponding choice in this route
Plan repeatable productionFor Stable Cascade, allocate 4–24 steps to the second stage In Stable Cascade, this capability is applied through the exact stability-ai/stable-cascade workflow with prompt as a relevant request control; the prompt control exposes the corresponding choice in this route
Confirm cost and deliveryUse the pricing combinations below and the output contract above when budgeting or automating Stable Cascade jobs.

Prompt Guide

Build the request around the exact stability-ai/stable-cascade schema. Start with required fields, then add only the controls needed for the intended output; keep URLs reachable and enum values exactly as shown in Technical Specs.

{
  "prompt": "An image of a shiba inu, donning a spacesuit and helmet",
  "seed": 0,
  "aspect_ratio": "21:9",
  "guidance_scale": 4
}

Technical Specs

SpecificationValue
Model IDstability-ai/stable-cascade
Execution modeasync
Required inputsprompt
Request fieldsseed (integer, optional); prompt (string, required); aspect_ratio (string, optional, options: 21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16); guidance_scale (number, optional, min 0, max 20); first_stage_steps (integer, optional, min 4, max 40); second_stage_steps (integer, optional, min 4, max 24); second_stage_guidance_scale (number, optional, min 0, max 20)
Outputurl (string); content_type (string)

Related Models

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Endpoint
https://api.sandbase.ai/v1/run
Model ID
stability-ai/stable-cascade
# Preserve Unicode and shell metacharacters in the request body.
result=$(printf '%s' 'ewogICJtb2RlbCI6ICJzdGFiaWxpdHktYWkvc3RhYmxlLWNhc2NhZGUiLAogICJwcm9tcHQiOiAiQW4gaW1hZ2Ugb2YgYSBzaGliYSBpbnUsIGRvbm5pbmcgYSBzcGFjZXN1aXQgYW5kIGhlbG1ldCIsCiAgImd1aWRhbmNlX3NjYWxlIjogNCwKICAiZmlyc3Rfc3RhZ2Vfc3RlcHMiOiAyMCwKICAic2Vjb25kX3N0YWdlX3N0ZXBzIjogMTAsCiAgInNlY29uZF9zdGFnZV9ndWlkYW5jZV9zY2FsZSI6IDAKfQ==' \
  | base64 --decode \
  | curl --fail-with-body --silent \
      -X POST "https://api.sandbase.ai/v1/run" \
      -H "Authorization: Bearer $SANDBASE_API_KEY" \
      -H "Content-Type: application/json" \
      --data-binary @-)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
Stable CascadeThis model
Stability AI		———Jun 25, 2024
SoteDiffusion
Stability AI		———Jun 10, 2024
ControlNet SDXL
Stability AI		———Feb 28, 2024
ControlNet SDXL
Stability AI		———Dec 1, 2023
Stable Diffusion XL
Stability AI		———Apr 16, 2024
Stable Diffusion XL
Stability AI		———Apr 16, 2024