Model List

For models that have a corresponding blog post, we've linked it in the model's title.

Text Generation

• DeepSeek-V3-0324: The leading non-reasoning model.

• DeepSeek-R1-Distill-Llama-70B: High-quality text generation for complex queries.

• DeepSeek-R1-Distill-Qwen-32B: Efficient text generation with lower resource usage.

• Llama3.3-70B: Advanced conversational AI with extensive knowledge.

• Qwen-QwQ-32B: The AI model from the Qwen series, designed for reasoning and problem-solving.

• Qwen2.5-Coder-32B: Specialized in code generation and completion.

Vision Models

• Qwen2.5-VL-7B-Instruct: An advanced vision-lanauge model designed to understand and process both visual and textual inputs.

Embedding Generation

• UAE-Large-V1: Good for general-purpose text embeddings with high accuracy.

• BGE Large EN v1.5: Optimized for English text embeddings with enhanced performance.

Image Generation

Text-to-Image

• StableDiffusion XL 1.0: enerates high-quality images from text prompts with detailed control.

• Flux.1 schnell: Fast text-to-image generation with efficient processing and good quality results.

Image-to-Image

• Flux.1 Fill Dev: Specialized in image inpainting, replacing selected areas based on text prompts and masks.