Overview
MythIQ provides access to a wide range of AI models from various providers through a unified API. Models are organized by type (image generation, video generation, etc.) and can be accessed using a consistent format regardless of the underlying provider.
Model Versioning
Models may have multiple versions. You can specify a version using the format base/model:version. If no version is specified, the latest version will be used.
Model Selection
When choosing a model, consider your specific requirements for quality, speed, and cost. Our intelligent routing can help select the optimal model based on your priorities.
Model Format
Models in MythIQ are identified using a consistent format: base/model[:version]
The model provider or family (e.g., openai, stability, anthropic)
The specific model name (e.g., dall-e-3, sdxl)
Optional. The specific version of the model (e.g., 1.0, 2.1)
Examples
openai/dall-e-3Latest version of OpenAI's DALL-E 3stability/sdxl:1.0Version 1.0 of Stability AI's SDXLanthropic/claude-3Latest version of Anthropic's Claude 3Image Generation Models
openai/dall-e-3
OpenAI's DALL-E 3 model for generating high-quality images from text descriptions.
Supported Sizes
Special Parameters
| Parameter | Type | Description |
|---|---|---|
| quality | string | "standard" or "hd" (default: "standard") |
| style | string | "vivid" or "natural" (default: "vivid") |
Example
import OpenAI from 'openai';
const openai = new OpenAI({
baseURL: 'https://api.mythiq.ai/v1',
apiKey: 'YOUR_API_KEY',
});
async function generateImage() {
const response = await openai.images.generate({
model: 'openai/dall-e-3',
prompt: 'A futuristic city with flying cars and neon lights',
size: '1024x1024',
quality: 'hd',
style: 'vivid',
});
console.log(response.data);
}stability/sdxl
Stability AI's SDXL model for generating detailed and creative images.
Supported Sizes
Special Parameters
| Parameter | Type | Description |
|---|---|---|
| cfg_scale | number | How closely to follow the prompt (1-35, default: 7) |
| steps | number | Number of diffusion steps (10-150, default: 30) |
| seed | number | Random seed for reproducibility (optional) |
Example
import OpenAI from 'openai';
const openai = new OpenAI({
baseURL: 'https://api.mythiq.ai/v1',
apiKey: 'YOUR_API_KEY',
});
async function generateImage() {
const response = await openai.images.generate({
model: 'stability/sdxl',
prompt: 'A serene landscape with mountains and a lake at sunset',
size: '1024x1024',
cfg_scale: 10,
steps: 50,
seed: 12345,
});
console.log(response.data);
}Video Generation Models
runway/gen-2
Runway's Gen-2 model for generating videos from text descriptions or image inputs.
Supported Sizes
Special Parameters
| Parameter | Type | Description |
|---|---|---|
| image_url | string | URL of an image to use as the starting point (optional) |
| duration | number | Duration in seconds (2-8, default: 4) |
Example
import { fetch } from 'cross-fetch';
async function generateVideo() {
const response = await fetch('https://api.mythiq.ai/v1/videos/generations', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'Authorization': 'Bearer YOUR_API_KEY',
},
body: JSON.stringify({
model: 'runway/gen-2',
prompt: 'A camera flying through a dense forest with sunlight streaming through the trees',
size: '1080p',
duration: 6,
}),
});
const data = await response.json();
console.log(data);
}Available Models
For a complete and up-to-date list of available models, you can use the Models API endpoint:
curl https://api.mythiq.ai/v1/models \
-H "Authorization: Bearer YOUR_API_KEY"This endpoint returns detailed information about all available models, including their capabilities, supported parameters, and pricing information.