SDXL
Description
Stable Diffusion XL (SDXL) is a high-quality AI image generator that creates detailed images from text prompts with improved realism and control.
At a Glance
Key pricing and model details available for this model.
Starting price
$0.0094
per image
Hallucination rate
0%
Supported sizes
512x512, 768x768, 1024x1024, 1408x1408, 576x1024, 1024x576, 768x1024, 1024x768
Image Pricing
Image generation pricing currently exposed by the models API.
Starting price
$0.0094
per image
Resolution Pricing
Resolution-specific prices returned for this image model.
| 1024x1024 | $0.0094 |
| 1024x576 | $0.0094 |
| 1024x768 | $0.0094 |
| 1408x1408 | $0.0094 |
| 512x512 | $0.0094 |
| 576x1024 | $0.0094 |
| 768x1024 | $0.0094 |
| 768x768 | $0.0094 |
| auto | $0.0094 |
Image Details
Additional image-related pricing and format support.
| Pricing unit | per image |
| Supported sizes | 512x512 768x768 1024x1024 1408x1408 576x1024 1024x576 768x1024 1024x768 |
Feature Availability
Capabilities explicitly listed in the current payload.
Image
Available
Vision
Not listed
Function calling
Not listed
Reasoning
Not listed
Artificial Analysis
Index scores currently reported for this model.
Intelligence Index
18.8
Coding Index
13.6
Math Index
30.3
Category Radar
Aggregated from the benchmark values present for reasoning, code, math, and accuracy.
Benchmark Breakdown
Detailed benchmark results drawn from the current payload.
Intelligence Index
Overall 'how smart' score for an AI, combining reasoning, math, coding, and knowledge.
18.8
Reported score
Coding Index
How well the model handles real programming tasks.
13.6
Reported score
Math Index
Composite score measuring mathematical reasoning and problem-solving.
30.3
Reported score
MMLU-Pro
A broad and difficult knowledge-and-reasoning benchmark across many subjects.
76%
Reported score
GPQA
Graduate-level science questions designed to be difficult to shortcut.
57.8%
Reported score
HLE
A very hard expert-level exam across a wide range of subjects.
4.3%
Reported score
LiveCodeBench
Fresh programming tasks meant to test current coding ability.
40%
Reported score
SciCode
Coding tasks drawn from real scientific workflows.
33.1%
Reported score
MATH-500
A set of difficult competition-style math problems.
90.7%
Reported score
AIME
Advanced math competition questions.
44%
Reported score
AIME 2025
The 2025 AIME benchmark used to reduce data leakage concerns.
30.3%
Reported score
IFBench
Measures how precisely the model follows detailed instructions.
39.3%
Reported score
LCR
Tests long-context reasoning over large documents and conversations.
28.0%
Reported score
TerminalBench Hard
A harder coding-agent benchmark for complex multi-step terminal tasks.
3.8%
Reported score
Tau2
Evaluates realistic agent behavior in tool-using support workflows.
24.3%
Reported score
Code Samples
Quick start with the Routeway API
const response = await fetch('https://api.routeway.ai/v1/images/generations', {
method: 'POST',
headers: {
'Authorization': 'Bearer <YOUR_API_KEY>',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'sdxl',
prompt: 'A futuristic city skyline at sunset',
size: '1024x1024',
})
});
const imageData = await response.json();
console.log(imageData);