# Selecting AI Models
## **Models We Integrate**
Aerogram is designed to be a versatile AI workflow platform, integrating with a wide array of leading artificial intelligence models to cater to diverse output needs. This allows you to select the best-suited AI for your specific task, ensuring optimal results.
### **Text Output Models**
* **Models for General Text Output:** Ideal for content generation, summarization, translation, and conversational AI, producing coherent text e.g. Claude, Deepseek, Llama, GPT, Perplexity.
* **Models for Text-Reasoning:** These models excel at complex analytical tasks, logical inference, problem-solving, and code generation, designed for deeper cognitive processing and structured output e.g. Claude, Gemini, Perplexity.
### **Image Output Models**
* **Models for Text-to-Image:** These models generate unique images from a textual description (your prompt) e.g. Flux, Luma Photon, DALL-E.
* **Models for Image-to-Image:** These models transform an existing image based on new instructions or a reference image e.g. Flux, Gemini.
* **Models for Multi-Image-to-Image:** These models take multiple input images and generate a new image, often combining elements or styles from the inputs e.g. Flux, Gemini.
### **Video Output Models**
* **Models for Text-to-Video:** These models create video clips directly from a textual description or script e.g. Kling, Luma Ray, Pika.
* **Models for Image-to-Video:** These models animate or transform static images into dynamic video sequences e.g. Hunyuan, Kling, Luma Ray.
