Model Overview
Infyr.AI provides access to a comprehensive collection of state-of-the-art AI models across different modalities. All models are accessible through our OpenAI-compatible API, making integration seamless with existing applications.
Model Categories
Text Generation Models
We offer a variety of text generation models optimized for different use cases:
- General Purpose: DeepSeek, Llama, Hermes models for general text generation
- Code Generation: Specialized models like Qwen-Coder for programming tasks
- Reasoning: Advanced models like DeepSeek-R1 for complex reasoning tasks
- High Context: Models with extended context windows for long-form content
Vision Models
Multi-modal models that can process and understand images alongside text:
- General Vision: Llama-3.2-Vision for image understanding
- High Performance: Qwen2.5-VL for advanced vision tasks
Embedding Models
Text embedding models for semantic search and similarity tasks:
- Multilingual: Support for multiple languages
- Modern Architecture: Latest embedding model architectures
Audio Models
Audio processing capabilities:
- Speech-to-Text: Whisper model for transcription
- Text-to-Speech: PlayAI TTS for voice synthesis
Video Models
Video generation and processing:
- Video Generation: Veo3 and Pixverse models for creating videos from text
- Multiple Formats: Support for different aspect ratios and durations
Usage Patterns
All models follow the same OpenAI-compatible API patterns:
const response = await openai.chat.completions.create({
model: "model-name",
messages: [...],
// model-specific parameters
});Pricing
Models are priced based on:
- Input/Output Tokens: For text models
- Duration: For audio and video generation
- Processing Time: For embedding and vision tasks
For detailed pricing information, visit our pricing page (opens in a new tab).
Getting Started
Choose the appropriate model category from the navigation to see detailed examples and usage patterns for each model type.