Model List

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

Multimodal

Claude-Sonnet-4: Anthropic's mid-size model with superior intelligence for high-volume uses in coding, in-depth research, agents, & more
Gemini-2.5-Flash-Preview-05-20: Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.
Gemini-2.5-Pro-Preview-06-05: Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.
Gemini-2.5-Pro-Preview-05-06: Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks
Gemini-2.0-Flash: Gemini 2.0 Flash delivers next-gen features and improved capabilities, including superior speed, built-in tool use, multimodal generation, and a 1M token context window
gpt-4o-mini: GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.

DeepSeek-R1-0528 (free): The latest state-of-the-art LLM released by Deepseek excels in reasoning, math, and coding. Community-shared access, daily limits, great for testing and exploration
DeepSeek-V3-0324 (free): The most powerful AI-driven LLM with 685B parameters released by Deepseek. Community-shared access, daily limits, great for testing and exploration
DeepSeek-V3-0324: DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team..
DeepSeek-R1 (free): A state-of-the-art, high-efficiency LLM excelling in reasoning, math, and coding. Community-shared access, daily limits, great for testing and exploration
DeepSeek-R1-0528: The latest state-of-the-art LLM released by Deepseek excels in reasoning, math, and coding. Community-shared access, daily limits, great for testing and exploration
DeepSeek-R1: A state-of-the-art, high-efficiency LLM excelling in reasoning, math, and coding. Community-shared access, daily limits, great for testing and exploration
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.

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.
Bytedance-Seedream-3.0: A top-tier bilingual text-to-image model rivaling GPT-4. Native 2K resolution, fast generation, accurate text, artistic layouts, and stunning detail
FLUX.1 [Fill-dev]: A 12 billion parameter inpainting model for editing and extending images
Qwen2.5-VL-7B-Instruct: An advanced vision-lanauge model designed to understand and process both visual and textual inputs.

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.
M2-BERT-Retrieval-32k: An 80M checkpoint of M2-BERT, pretrained with sequence length 32768, and it has been fine-tuned for long-context retrieval.

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

Coming soon

Last updated 1 month ago