A state-of-the-art text generation model with 358B parameters, supporting English and Chinese, optimized for agentic reasoning, coding, and complex tool use.

MiniMax M2.1 is a state-of-the-art (SOTA) model designed specifically for real-world development and autonomous agents, focusing on coding, tool use, and long-horizon planning.

Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base

The Qwen3-TTS-Tokenizer-12Hz model which can encode the input speech into codes and decode them back into speech.

A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on Your Phone

DeepSeek-OCR is a model designed to explore the boundaries of visual-text compression, investigating the role of vision encoders from an LLM-centric viewpoint.

GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture

PaddleOCR-VL-1.5 is an advanced next-generation model of PaddleOCR-VL, achieving a new state-of-the-art accuracy of 94.5% on OmniDocBench v1.5

The Qwen3-ASR family includes Qwen3-ASR-1.7B and Qwen3-ASR-0.6B, which support language identification and ASR for 52 languages and dialects.

an open-weight language model designed specifically for coding agents and local development

An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Convert speech in audio to text

OpenAI's Most advanced synced-audio video generation

OpenAI's latest image generation model with better instruction following and adherence to prompts

A powerful native multimodal model for image generation (PrunaAI squeezed)

A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, thanks to Query-Key Normalization.

Google's latest image editing model in Gemini 2.5

A sub 1 second text-to-image model built for production use cases.

Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis

Use this ultra version of Imagen 4 when quality matters more than speed and cost

Seedream 4.5: Upgraded Bytedance image model with stronger spatial understanding and world knowledge

The highest fidelity image model from Black Forest Labs

An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering.

Google's state of the art image generation and editing model 🍌🍌