---
title: Stable Diffusion API — SDXL, SD 3, ControlNet | ModelsLab
description: Stable Diffusion API for production — SDXL, SD 3 Medium, ControlNet, LoRA and inpainting on one REST endpoint. $0.0047/image list price, plans from $21/month.
url: https://modelslab.com/stable-diffusion-api
canonical: https://modelslab.com/stable-diffusion-api
type: website
component: Seo/StableDiffusionApi
generated_at: 2026-11-12T01:40:23.490369Z
---
Imagen
Stable Diffusion API for Developers
---
ModelsLab's Stable Diffusion API gives developers SDXL, SD 1.5 and SD 3 Medium — plus ControlNet, LoRA, inpainting, and 10,000+ community checkpoints — through one REST endpoint. Image generation is $0.0047 per image from your plan's included usage, with 2-4 second latency on warm models — plans from $21/month.
[Get Your Stable Diffusion API Key](https://modelslab.com/register) [API Documentation](https://docs.modelslab.com)
Last updated Nov 4, 2026 · By ModelsLab Engineering
Stable Diffusion API (stablediffusionapi.com) is now part of ModelsLab: SD 1.5, SDXL, SD 3 Medium, ControlNet and community checkpoints all run on this API.
How can I run SDXL as a hosted API?
---
Get an API key, then POST your key, a prompt and `"model_id": "sdxl"` to `https://modelslab.com/api/v7/images/text-to-image`. The JSON response has hosted image URLs, or an id to fetch while the image renders. You do not rent a GPU, load weights or keep a server warm: ModelsLab runs SDXL for you at $0.0047 per image from your plan. To use a community checkpoint or your own fine-tune, change only model\_id.
How much does Stable Diffusion cost through an API in 2026?
---
On ModelsLab, an SDXL or SD 1.5 image is $0.0047 on the $47/month Standard plan (10,000 API calls) and $0.0065 on the $21/month Basic plan (3,250 calls). The $149/month Open Source Unlimited plan has no per-image charge on the Stable Diffusion models we host, which works out to $0.0015 per image at 100,000 images a month.
Stability AI's own API bills credits at $0.01 each: SDXL 1.0 from $0.009 per image, SD 3.5 Medium $0.035, SD 3.5 Large $0.065 and Stable Image Ultra $0.08. Replicate lists SD 3.5 Large at the same $0.065 per image, and fal at $0.065 per megapixel. The cheapest per image is SDXL on Replicate, billed by GPU time at about $0.0026 an image, which beats every ModelsLab plan up to about 57,000 images a month. Above that, the flat plan is cheaper. ModelsLab does not host SD 3.5: for SD 3.5, use Stability AI, Replicate or fal.
Stable Diffusion API Price per Image, September 2026
---
List prices from each provider's own pricing page. Per-image prices are for one 1024×1024 image; fal bills per megapixel.
| Provider | Model | Listed price | How it is billed |
|---|---|---|---|
| ModelsLab | SDXL, SD 1.5, SD 3 Medium | $0.0047 (Standard), $0.0065 (Basic) | $47/month for 10,000 calls, $21/month for 3,250 |
| ModelsLab | Same models, Open Source Unlimited | No per-image charge ($0.0015 at 100,000 images) | $149/month |
| Stability AI | SDXL 1.0 | From $0.009 | Credits at $0.01, bought in $10 steps |
| Stability AI | Stable Image Core | $0.03 | Credits |
| Stability AI | SD 3.5 Medium | $0.035 | Credits |
| Stability AI | SD 3.5 Large Turbo | $0.04 | Credits |
| Stability AI | SD 3.5 Large | $0.065 | Credits |
| Stability AI | Stable Image Ultra | $0.08 | Credits |
| Replicate | SDXL | About $0.0026 | GPU time, $0.000975 per second on an L40S |
| Replicate | SD 3.5 Medium | $0.035 | Per output image |
| Replicate | SD 3.5 Large | $0.065 | Per output image |
| fal | SD 3.5 Large Turbo | $0.015 | Per megapixel |
| fal | SD 3.5 Medium | $0.02 | Per megapixel |
| fal | SD 3.5 Large | $0.065 | Per megapixel |
Prices checked September 27, 2026 on platform.stability.ai/pricing (1 credit = $0.01; SDXL 1.0 from 0.9 credits for a 1024×1024 image, SD 3.5 Medium 3.5, SD 3.5 Large Turbo 4, SD 3.5 Large 6.5, Stable Image Ultra 8), replicate.com (SD 3.5 Large $0.065, Large Turbo $0.04 and Medium $0.035 per output image; SDXL billed by GPU time on an L40S at $0.000975 per second, which Replicate estimates at about $0.0026 per run) and fal.ai (SD 3.5 Large $0.065, Medium $0.02 and Large Turbo $0.015 per megapixel). ModelsLab prices are the plan price divided by its call limit.
SDXL Cost at 1,000 to 500,000 Images a Month
---
Monthly cost for one SDXL image per call at 1024×1024, on the smallest ModelsLab plan whose call limit covers the volume.
| Images / month | Replicate SDXL (~$0.0026) | Stability AI SDXL ($0.009) | ModelsLab | Cheapest |
|---|---|---|---|---|
| 1,000 | $2.60 | $9 | $21 Basic | Replicate |
| 10,000 | $26 | $90 | $47 Standard | Replicate |
| 50,000 | $130 | $450 | $149 Open Source Unlimited | Replicate |
| 100,000 | $260 | $900 | $149 Open Source Unlimited | ModelsLab |
| 500,000 | $1,300 | $4,500 | $149 Open Source Unlimited | ModelsLab |
Prices checked September 27, 2026. Replicate SDXL is billed by the second, so its cost moves with steps and resolution; the $0.0026 per image here is Replicate's own estimate. Stability AI SDXL 1.0 is from 0.9 credits ($0.009) per image.
What is the ModelsLab Stable Diffusion API?
---
### Production Stable Diffusion, One REST Endpoint
The ModelsLab Stable Diffusion API gives developers programmatic access to the full Stable Diffusion family — SDXL, SD 1.5 and SD 3 Medium — plus 10,000+ community checkpoints and LoRAs, all through a single REST endpoint. You pass a model\_id and a prompt to /api/v7/images/text-to-image and receive hosted image URLs in JSON within a few seconds.
Stable Diffusion is the most widely used open image-generation model family, and running it well in production means managing GPUs, model loading, VRAM, and scaling. ModelsLab handles all of that: popular models stay warm, a rarely used checkpoint or LoRA loads onto a GPU on first use (a few minutes), and auto-scaling absorbs traffic spikes. You keep the Stable Diffusion workflow you already know and drop the infrastructure.
Beyond base models, the API exposes the tools Stable Diffusion developers rely on — ControlNet for structural guidance, LoRA for style and subject fine-tuning, and dedicated inpainting and image-to-image endpoints. The same API key also covers FLUX and 10,000+ other image, video, audio, and LLM models when your product grows.
### What You Can Build with the Stable Diffusion API
The Stable Diffusion API supports the full range of image workflows through one key:
- Text-to-Image — Generate images from prompts with SDXL, SD 1.5 or SD 3 Medium at up to 2048×2048
- Image-to-Image — Transform existing images with strength-controlled, prompt-guided edits
- Inpainting — Mask a region and regenerate it from a prompt for object removal and replacement
- ControlNet — Guide generation with pose, depth, edge, and segmentation reference maps
- LoRA & Custom Checkpoints — Attach community LoRAs or upload and serve your own fine-tuned models
- Upscaling — Enhance output resolution with super-resolution models through the same API
Trusted by
500M+
API Requests Processed
400K+
Registered Users
5K+
Discord Community Members
300+
Available AI APIs
500
GPUs in Our Own Datacenter
Stable Diffusion Models on One API
---
Every major Stable Diffusion base model, selected with a single model\_id. Every one of them is $0.0047 per image from your plan, or unlimited on the $149 plan.
| Model | Best for | Native resolution | ModelsLab price |
|---|---|---|---|
| sdxl | High-quality general-purpose generation and photorealism | 1024×1024 | $0.0047/image |
| stable-diffusion-3-medium | Better prompt following and text in images than SDXL | 1024×1024 | $0.0047/image |
| sd-1.5 | Fast generation and the largest community LoRA ecosystem | 512×512 | $0.0047/image |
Stable Diffusion API Quick Start
---
Generate an image in seconds with a single REST call — cURL, Python, or JavaScript.
### Generate with SDXL using cURL
curl
```
1curl -X POST "https://modelslab.com/api/v7/images/text-to-image" \
2 -H "Content-Type: application/json" \
3 -d '{
4 "key": "YOUR_API_KEY",
5 "model_id": "sdxl",
6 "prompt": "a cozy reading nook by a rainy window, warm light, photorealistic",
7 "negative_prompt": "blurry, distorted, low quality",
8 "width": 1024,
9 "height": 1024,
10 "samples": 1,
11 "num_inference_steps": 30,
12 "guidance_scale": 7.5
13 }'
```
### Generate with Python (SD 3 Medium)
Python
```
1import requests
2
3url = "https://modelslab.com/api/v7/images/text-to-image"
4payload = {
5 "key": "YOUR_API_KEY",
6 "model_id": "stable-diffusion-3-medium",
7 "prompt": "isometric illustration of a solar-powered smart home, clean vector style",
8 "width": 1024,
9 "height": 1024,
10 "samples": 2,
11 "num_inference_steps": 28,
12 "guidance_scale": 4.5
13}
14
15response = requests.post(url, json=payload)
16data = response.json()
17
18# data["output"] is a list of generated image URLs
19for i, image_url in enumerate(data["output"]):
20 print(f"Image {i+1}: {image_url}")
```
### Inpainting with JavaScript
JavaScript
```
1const response = await fetch('https://modelslab.com/api/v7/images/inpaint', {
2 method: 'POST',
3 headers: { 'Content-Type': 'application/json' },
4 body: JSON.stringify({
5 key: 'YOUR_API_KEY',
6 model_id: 'sdxl',
7 init_image: 'https://example.com/photo.jpg',
8 mask_image: 'https://example.com/mask.png',
9 prompt: 'replace with a bouquet of white peonies',
10 samples: 1
11 })
12});
13
14const data = await response.json();
15// data.output = array of inpainted image URLs
16data.output.forEach((url, i) => console.log(`Result ${i + 1}: ${url}`));
```
One API: SDXL, SD 3, ControlNet & LoRA
---
Text-to-image, image-to-image, inpainting, ControlNet guidance, and custom checkpoints — all behind a single Stable Diffusion endpoint and one API key.
Every Stable Diffusion Base Model SDXL, SD 1.5 and SD 3 Medium are all available through the same text-to-image endpoint. Switch model\_id to move between speed, resolution, and quality without changing your integration.
ControlNet & LoRA Built In Use ControlNet for pose, depth, edge, and segmentation guidance, and attach community LoRAs to steer style. Both run through the standard API — no custom pipeline assembly required.
Inpainting & Image-to-Image Dedicated /inpaint and /image-to-image endpoints handle masked edits, object removal, and strength-controlled transformations, so editing workflows are a single call.
Custom Checkpoints Upload your own fine-tuned Stable Diffusion or SDXL checkpoints and serve them through the same endpoint as the base models — ideal for brand-specific pipelines.
Everything developers need to ship Stable Diffusion features in production.
[Get Started](https://modelslab.com/register)
Stable Diffusion API Comparison
---
How ModelsLab compares to other ways to run Stable Diffusion in production.
| Feature | ModelsLab | Self-hosted GPU | Generic serverless |
|---|---|---|---|
| Models available | SDXL, SD 1.5, SD 3 + 10,000+ | Whatever you install | A handful, provider-picked |
| ControlNet & LoRA | Built in | DIY setup | Varies |
| Inpainting & image-to-image | Dedicated endpoints | DIY | Varies |
| Cold starts | Popular models warm | None (always on) | Frequent |
| GPU / DevOps to manage | None | All of it | None |
| Cost model | $0.0047/image or $149/mo unlimited | Fixed GPU rental + ops time | Per-second, spiky |
| Free tier | Paid, from $21/mo | No | Trial credits |
Data as of July 2026. Self-hosted and serverless figures reflect typical setups; your costs will vary with hardware, utilization, and traffic pattern.
Related image API guides
---
[### Image Generation API
Full catalog: SDXL, SD 3, FLUX, and 10,000+ models through one endpoint.](https://modelslab.com/image-generation-api) [### Flux API
FLUX.1 Schnell, Dev, Pro, and Kontext via the same REST API and key.](https://modelslab.com/flux-api) [### ComfyUI API
Run ComfyUI workflows in the cloud without self-hosting the pipeline.](https://modelslab.com/comfyui-api) [### AI Image Generation API
The prompt-to-image endpoint reference for Flux, SDXL and 10,000+ models.](https://modelslab.com/image-generation-api) [### Image Editing API
Inpainting, outpainting, object removal and upscaling on the same key.](/image-editing-api) [### OpenAI API Alternative
Open-weight models on flat plans, OpenAI SDK unchanged.](/openai-api-alternative)
How to Use the Stable Diffusion API
---
Generate your first image in under 5 minutes.
STEP 01
STEP 01
### Step 1: Get Your API Key
Create a ModelsLab account, subscribe to a plan (from $21/month), and generate your API key from the dashboard. Every plan includes SDXL, SD 3 Medium, ControlNet, and inpainting.
STEP 02
STEP 02
### Step 2: Choose a Model and Prompt
Send a POST request to /api/v7/images/text-to-image with model\_id set to sdxl, stable-diffusion-3-medium, or any community checkpoint, plus your prompt and parameters like width, height, and steps.
STEP 03
STEP 03
### Step 3: Get Your Images
Receive hosted image URLs in the JSON response within a few seconds. Use the /inpaint and /image-to-image endpoints for masked edits and transformations.
[Start Generating with Stable Diffusion ](https://modelslab.com/register)
### Stable Diffusion API Pricing
The Stable Diffusion API uses simple pricing: $0.0047 per image from the usage included in your plan ($47 on Standard covers 10,000 images), the same across SDXL, SD 1.5 and SD 3 Medium with no resolution upcharge up to 2048×2048. Stability AI’s own API lists SDXL 1.0 from $0.009 per image; Replicate bills SDXL by GPU time at about $0.0026 per image, which is cheaper than any ModelsLab plan below about 57,000 images a month (prices checked 2026-09-27).
For high-volume workloads, the $149/month Open Source Unlimited plan removes per-image cost entirely — the cheapest option at scale. Paid plans start at $21/month (Basic) and $47/month (Standard), and dedicated enterprise endpoints with custom SLAs start at $249/month. Compared with self-hosting, you avoid GPU rental, VRAM tuning, and on-call ops entirely.
### API Response Format
The Stable Diffusion API returns a consistent JSON response across all endpoints. Generated images come back as publicly accessible URLs (available for 24 hours) or as base64 data for direct embedding. Synchronous requests return images in the response; for longer or batched jobs, use asynchronous mode and poll the fetch endpoint with the returned request\_id, or register a webhook to receive completions.
### Integration and SDKs
ModelsLab provides SDKs and integration paths for the Stable Diffusion API across popular stacks:
- Python SDK — pip install modelslab — full endpoint coverage with async support
- JavaScript/TypeScript — npm install modelslab — works in Node.js, Deno, and the browser
- REST API — standard HTTP endpoints usable from any language (cURL, Go, Ruby, PHP, Java)
- Webhook callbacks — receive generation completion notifications for async pipelines
- Documentation — per-parameter guides and examples at docs.modelslab.com
Why ModelsLab for the Stable Diffusion API?
---
Key advantages that set us apart
SDXL, SD 1.5, SD 3 Medium plus 10,000+ checkpoints on one endpoint
$0.0047 per image with no resolution upcharge, unlimited on the $149 plan
$149/mo unlimited plan for high-volume generation
ControlNet for pose, depth, edge, and segmentation guidance
LoRA support and custom checkpoint upload
Dedicated inpainting and image-to-image endpoints
Popular models stay warm; rarely used ones load on first use
No GPU, VRAM, or DevOps to manage
FLUX and 10,000+ other models on the same key
Plans start at $21/month (Basic, 3,250 API calls)
Our Popular Use Cases
What developers build with the Stable Diffusion API:
Design & Creative ToolsE-Commerce Product ImageryMarketing Creative AutomationCustom-Style ProductsControlNet WorkflowsContent Platforms
Embed Stable Diffusion generation and editing into design apps, letting users create, transform, and inpaint images on demand.
Related Image APIs
---
- [AI Image Generation API](/image-generation-api)Text to image, image to image and inpainting on one endpoint.
- [Cheapest image generation API](/cheapest-ai-image-api)Cost per image at 3,250 to 500,000 images a month.
- [Flux API](/flux-api)Flux models over REST, self-hosted.
- [Best AI image generation APIs in 2026](/best-ai-image-generation-api-2026)Providers compared on price, speed and models.
- [Cheapest AI API](/cheapest-ai-api)Image, video and speech prices side by side.
- [Unlimited AI API](/unlimited)Every self-hosted open-source model for $149/mo.
Stable Diffusion API FAQ
---
### What is the Stable Diffusion API?
The Stable Diffusion API is a REST API for generating and editing images with the Stable Diffusion model family. ModelsLab exposes SDXL, SD 1.5 and SD 3 Medium — plus ControlNet, LoRA, inpainting, and 10,000+ community checkpoints — through a single endpoint at /api/v7/images/text-to-image, so you can generate from text or edit existing images with a single model_id change.
On ModelsLab, Stable Diffusion image generation is $0.0047 per image on the $47/month Standard plan (10,000 API calls) and $0.0065 on the $21/month Basic plan (3,250 calls), the same across SDXL, SD 1.5 and SD 3 Medium with no resolution upcharge up to 2048×2048. The $149/month Open Source Unlimited plan has no per-image charge, and enterprise dedicated endpoints start at $249/month.
### Which Stable Diffusion models are supported?
SDXL, SD 1.5 and SD 3 Medium are supported, alongside 10,000+ community fine-tuned checkpoints and LoRAs. You select any of them with the model_id parameter, and you can also upload and serve your own fine-tuned checkpoints.
### Does the API support ControlNet, LoRA, and inpainting?
Yes. ControlNet (pose, depth, edge, segmentation), LoRA styling, and dedicated inpainting and image-to-image endpoints are all available through the same API key. Text-to-image, image-to-image, inpainting, and ControlNet share one integration.
### How is this different from self-hosting Stable Diffusion?
Self-hosting means renting GPUs and managing model loading, VRAM, scaling, and on-call operations. The ModelsLab API removes all of that: popular models stay warm (a rarely used checkpoint or LoRA loads on first use), auto-scaling absorbs spikes, and you pay $0.0047 per image from your plan or $149/month for unlimited generation instead of paying for idle GPU time.
Yes. Migration is an endpoint and payload swap: point text-to-image calls at /api/v7/images/text-to-image, image edits at /api/v7/images/image-to-image, and masked edits at /api/v7/images/inpaint. Your prompts, guidance settings, and ControlNet workflows carry over, and responses return hosted image URLs in JSON.
### Is there a free way to test the Stable Diffusion API?
ModelsLab is a paid service — plans start at $21/month (Basic, 3,250 API calls) and include SDXL, SD 1.5, SD 3 Medium, ControlNet, and inpainting. Creating an account is free; API generation requires an active plan. The $47/month Standard plan (10,000 API calls) suits production volume.
Your Data is Secure: GDPR Compliant AI Services
---
Plans from $21 a month
---
Basic is $21/month and Standard $47/month; self-hosted image models cost $0.0047 per image from that allowance. Open Source Unlimited is $149/month with no per-image charge on self-hosted models. Every plan covers Flux, SDXL and 10,000+ community models. Cancel anytime.
100% refund policy on monthly & yearly plans — cancel anytime
MonthlyYearly 2 Months Free
[Contact Sales](https://calendly.com/support-lael/30min)
Best Value
### Open Source Unlimited
Mission-Critical
$149 /month
Get API Key100% refund policy · cancel anytime
Unlimited Open Source Models
100% refund policy
24x7 Support
15 parallel generations
Access to all APIs
Unlimited generations on all open-source models
For mission critical workloads
Add Team Members
Priority GPU Clusters
Most Popular
### Standard
Production
$47 /month
Get API Key100% refund policy · cancel anytime
Moderate Traffic
100% refund policy
Priority Developer Support
10 concurrent API requests
For Production workloads
API access to all models
Prototype
### Basic
Prototype
$21 /month
Get API Key100% refund policy · cancel anytime
Moderate Traffic
100% refund policy
Developer Support via Discord/Email
5 concurrent API requests
API access to all models
Shared GPU
TestimonialsTrusted by 450+ teams on dedicated GPUs
---
See how developers and engineering teams scale generative pipelines with ModelsLab.
Previous slideNext slide
ModelsLab's Voice Cloning and Audio APIs revolutionized how we approach character development in our games. It's like having a full studio of voice actors running on dedicated infrastructure.
#### Alex Rivera
Lead Game Developer at Voxel Studios
The LLM and image generation APIs made multi-model pipelines trivial. One unified API key replaced four separate vendor contracts and cut our queue latency in half.
#### John Hernandez
AI Systems Architect at Synthetix AI
The ease of creating lifelike voiceovers for our e-learning courses has dramatically increased engagement. 99.9% uptime and instant API response have made it essential to our stack.
#### Priya Singh
Instructional Designer at LearnStream Media
Dedicated GPU clusters gave our production pipelines the throughput we needed without unpredictable rate limits or cold starts. Excellent developer experience.
#### Michael Chen
Digital Marketing Manager at Nexus Studio
Get expert support
We're Here to Help.
---
Want to know more? You can email us anytime at
Chat with support[View Docs](https://docs.modelslab.com)
ModelsLab serves SDXL, SD 1.5 and SD 3 Medium through one REST API, plus 10,000+ community checkpoints and LoRAs built on them. You select a model with a single model_id parameter (for example sdxl, sd-1.5 or stable-diffusion-3-medium), so you can move between base models and fine-tunes without changing your integration. ModelsLab does not host SD 3.5; for SD 3.5, use Stability AI, Replicate or fal.
Yes. The API exposes ControlNet for pose, depth, and edge guidance, LoRA support for style and subject fine-tuning, and dedicated inpainting and image-to-image endpoints. Text-to-image, image-to-image, inpainting, and ControlNet all run through the same API key.
On ModelsLab, a Stable Diffusion image is $0.0047 on the $47/month Standard plan (10,000 API calls) and $0.0065 on the $21/month Basic plan (3,250 calls), with no resolution upcharge up to 2048×2048. The $149/month Open Source Unlimited plan has no per-image charge, which is $0.0015 per image at 100,000 images a month. For comparison, Stability AI lists SDXL 1.0 from $0.009 per image and Replicate bills SDXL by GPU time at about $0.0026 per image. Prices checked 2026-09-27.
Send a POST request to https://modelslab.com/api/v7/images/text-to-image with your API key, model_id (for example "sdxl" or "stable-diffusion-3-medium"), and a prompt. Images are returned as hosted URLs in the JSON response, usually within a few seconds. Python, JavaScript, and cURL examples are documented at docs.modelslab.com.
Yes. If you already build with Stable Diffusion locally or on another host, migration is an endpoint and payload swap: point text-to-image calls at /api/v7/images/text-to-image, image edits at /api/v7/images/image-to-image, and masked edits at /api/v7/images/inpaint. Your prompts, guidance settings, and ControlNet workflows carry over.
ModelsLab's Stable Diffusion API is paid — plans start at $21/month (Basic, 3,250 API calls) and include SDXL, SD 1.5, SD 3 Medium, ControlNet, and inpainting. Popular models stay loaded on running workers; a rarely used community checkpoint can take a few minutes to load on its first request.
Between about $0.0015 and $0.08 per image, depending on the model and your volume. Stability AI bills credits at $0.01 each: SDXL 1.0 from $0.009 per image, SD 3.5 Medium $0.035, SD 3.5 Large $0.065 and Stable Image Ultra $0.08. Replicate bills SDXL by GPU time at about $0.0026 per image and SD 3.5 Large at $0.065. ModelsLab is $0.0047 per SDXL or SD 1.5 image on the $47 Standard plan, and the $149 Open Source Unlimited plan works out to $0.0015 per image at 100,000 images a month. Prices checked 2026-09-27.
Stability AI sells credits at $0.01 each, in $10 steps. On 2026-09-27 its pricing page listed SDXL 1.0 from 0.9 credits ($0.009) per 1024×1024 image, Stable Image Core 3 credits ($0.03), SD 3.5 Medium 3.5 ($0.035), SD 3.5 Large Turbo 4 ($0.04), SD 3.5 Large 6.5 ($0.065) and Stable Image Ultra 8 ($0.08).
For SDXL, yes. Replicate bills SDXL by GPU time at about $0.0026 per image, and ModelsLab is $0.0047 per image on the $47 Standard plan, against $0.009 on Stability AI. Replicate is the cheapest per image up to about 57,000 images a month; above that, the $149 ModelsLab Open Source Unlimited plan costs less because it has no per-image charge. For SD 3.5 Large, Stability AI and Replicate list $0.065 per image and fal $0.065 per megapixel. Prices checked 2026-09-27.
No. ModelsLab hosts SDXL, SD 1.5, SD 3 Medium and 10,000+ community checkpoints built on them, but not SD 3.5. For SD 3.5 Large, Large Turbo or Medium, use Stability AI, Replicate or fal.
Call a hosted endpoint instead of running your own GPU: POST https://modelslab.com/api/v7/images/text-to-image with your key, model_id sdxl and a prompt, and the response returns hosted image URLs (or posts them to your webhook). An SDXL image works out to $0.0047 on the $47/month Standard plan, and the $149/month Open Source Unlimited plan has no per-image charge on the Stable Diffusion models it hosts.
Explore Our Other Solutions
---
Unlock your creative potential and scale your business with ModelsLab's comprehensive suite of AI-powered solutions.
[Audio Gen
### AI Audio Generation
Text-to-speech, voice cloning, music generation, and audio processing APIs.
Explore Audio Gen](https://modelslab.com/audio-gen) [Video Fusion
### AI Video Generation & Tools
Create, edit, and enhance videos with AI-powered generation and transformation tools.
Explore Video Fusion](https://modelslab.com/video-generation) [Chat
### Engage Seamlessly with LLM
Access powerful language models for chatbots, content generation, and AI assistants.
Explore Chat](https://modelslab.com/chatbot-api) [3D Verse
### Create Stunning 3D Models
Transform images and text into 3D models with advanced AI-powered generation.
Explore 3D Verse](https://modelslab.com/text-to-3d)
Plugins
Explore Plugins for Pro
---
Our plugins are designed to work with the most popular content creation software.
[Explore Plugins](https://modelslab.com/pro#plugins) [About ModelsLab Pro](https://modelslab.com/pro)
API
Build Apps with ModelsLab
ML
API
---
Use our API to build apps, generate AI art, create videos, and produce audio with ease.
[API Documentation](https://docs.modelslab.com) [Playground](https://modelslab.com/models)
## Frequently Asked Questions
### Which Stable Diffusion models does the API support?
ModelsLab serves SDXL, SD 1.5 and SD 3 Medium through one REST API, plus 10,000+ community checkpoints and LoRAs built on them. You select a model with a single model_id parameter (for example sdxl, sd-1.5 or stable-diffusion-3-medium), so you can move between base models and fine-tunes without changing your integration. ModelsLab does not host SD 3.5; for SD 3.5, use Stability AI, Replicate or fal.
### Does the Stable Diffusion API support ControlNet, LoRA, and inpainting?
Yes. The API exposes ControlNet for pose, depth, and edge guidance, LoRA support for style and subject fine-tuning, and dedicated inpainting and image-to-image endpoints. Text-to-image, image-to-image, inpainting, and ControlNet all run through the same API key.
### How much does the Stable Diffusion API cost?
On ModelsLab, a Stable Diffusion image is $0.0047 on the $47/month Standard plan (10,000 API calls) and $0.0065 on the $21/month Basic plan (3,250 calls), with no resolution upcharge up to 2048×2048. The $149/month Open Source Unlimited plan has no per-image charge, which is $0.0015 per image at 100,000 images a month. For comparison, Stability AI lists SDXL 1.0 from $0.009 per image and Replicate bills SDXL by GPU time at about $0.0026 per image. Prices checked 2026-09-27.
### How do I call the Stable Diffusion API?
Send a POST request to https://modelslab.com/api/v7/images/text-to-image with your API key, model_id (for example "sdxl" or "stable-diffusion-3-medium"), and a prompt. Images are returned as hosted URLs in the JSON response, usually within a few seconds. Python, JavaScript, and cURL examples are documented at docs.modelslab.com.
### Can I migrate an existing Stable Diffusion integration?
Yes. If you already build with Stable Diffusion locally or on another host, migration is an endpoint and payload swap: point text-to-image calls at /api/v7/images/text-to-image, image edits at /api/v7/images/image-to-image, and masked edits at /api/v7/images/inpaint. Your prompts, guidance settings, and ControlNet workflows carry over.
### Is there a free Stable Diffusion API tier?
ModelsLab's Stable Diffusion API is paid — plans start at $21/month (Basic, 3,250 API calls) and include SDXL, SD 1.5, SD 3 Medium, ControlNet, and inpainting. Popular models stay loaded on running workers; a rarely used community checkpoint can take a few minutes to load on its first request.
### How much does it cost to use Stable Diffusion through an API in 2026?
Between about $0.0015 and $0.08 per image, depending on the model and your volume. Stability AI bills credits at $0.01 each: SDXL 1.0 from $0.009 per image, SD 3.5 Medium $0.035, SD 3.5 Large $0.065 and Stable Image Ultra $0.08. Replicate bills SDXL by GPU time at about $0.0026 per image and SD 3.5 Large at $0.065. ModelsLab is $0.0047 per SDXL or SD 1.5 image on the $47 Standard plan, and the $149 Open Source Unlimited plan works out to $0.0015 per image at 100,000 images a month. Prices checked 2026-09-27.
### How much does the Stability AI API cost per image?
Stability AI sells credits at $0.01 each, in $10 steps. On 2026-09-27 its pricing page listed SDXL 1.0 from 0.9 credits ($0.009) per 1024×1024 image, Stable Image Core 3 credits ($0.03), SD 3.5 Medium 3.5 ($0.035), SD 3.5 Large Turbo 4 ($0.04), SD 3.5 Large 6.5 ($0.065) and Stable Image Ultra 8 ($0.08).
### Is there a cheaper Stable Diffusion API than Stability AI?
For SDXL, yes. Replicate bills SDXL by GPU time at about $0.0026 per image, and ModelsLab is $0.0047 per image on the $47 Standard plan, against $0.009 on Stability AI. Replicate is the cheapest per image up to about 57,000 images a month; above that, the $149 ModelsLab Open Source Unlimited plan costs less because it has no per-image charge. For SD 3.5 Large, Stability AI and Replicate list $0.065 per image and fal $0.065 per megapixel. Prices checked 2026-09-27.
### Can I use Stable Diffusion 3.5 on ModelsLab?
No. ModelsLab hosts SDXL, SD 1.5, SD 3 Medium and 10,000+ community checkpoints built on them, but not SD 3.5. For SD 3.5 Large, Large Turbo or Medium, use Stability AI, Replicate or fal.
### How can I run SDXL as a hosted API?
Call a hosted endpoint instead of running your own GPU: POST https://modelslab.com/api/v7/images/text-to-image with your key, model_id sdxl and a prompt, and the response returns hosted image URLs (or posts them to your webhook). An SDXL image works out to $0.0047 on the $47/month Standard plan, and the $149/month Open Source Unlimited plan has no per-image charge on the Stable Diffusion models it hosts.
---
*This markdown version is optimized for AI agents and LLMs.*
**Links:**
- [Website](https://modelslab.com)
- [API Documentation](https://docs.modelslab.com)
- [Blog](https://modelslab.com/blog)
---
*Generated by ModelsLab - 2026-11-12*