Every open model, one platform

DeepSeek-V4-FlashDeepSeek · Language

Official

DeepSeek-V4-Flash with 284B parameters (13B activated) — both supporting a context length of one million tokens.

GLM-5.2Zhipu AI · Language

Official

GLM-5.2 marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a solid 1M-token context. GLM-5.2's new capabilities include: Solid 1M Context: A solid 1M-token context that stably sustains long-horizon work Advanced Coding with Flexible Effort: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency Improved Architecture: We propose IndexShare, which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9× at a 1M context length. We also improve GLM-5.2’s MTP layer for speculative decoding, increasing the acceptance length by up to 20% Pure Open: An MIT open-source license — no regional limits, technical access without borders

gpt-oss-20bOpenAI · Language

Official

gpt-oss-20b, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)

Llama-3.1-8B-InstructMeta · Language

Official

The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out). The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.

Qwen3.8-27BAlibaba · Vision

Official

Qwen3.8 27B dense vision-language model. Text + image input, 32K context, FP8. Supports tool/function calling and reasoning.

Qwen-ImageAlibaba · Image

Official

Qwen-Image, an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing. Experiments show strong general capabilities in both image generation and editing, with exceptional performance in text rendering, especially for Chinese.

Z-Image-TurboAlibaba · Image

Official

Z-Image is a powerful and highly efficient image generation model family with 6B parameters. Currently there are four variants: 🚀 Z-Image-Turbo – A distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers ⚡️sub-second inference latency⚡️ on enterprise-grade H800 GPUs and fits comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence. 🎨 Z-Image – The foundation model behind Z-Image-Turbo. Z-Image focuses on high-quality generation, rich aesthetics, strong diversity, and controllability, well-suited for creative generation, fine-tuning, and downstream development. It supports a wide range of artistic styles, effective negative prompting, and high diversity across identities, poses, compositions, and layouts. 🧱 Z-Image-Omni-Base – The versatile foundation model capable of both generation and editing tasks. By releasing this checkpoint, we aim to unlock the full potential for community-driven fine-tuning and custom development, providing the most "raw" and diverse starting point for the open-source community. ✍️ Z-Image-Edit – A variant fine-tuned on Z-Image specifically for image editing tasks. It supports creative image-to-image generation with impressive instruction-following capabilities, allowing for precise edits based on natural language prompts.

LTX 2.5Lightricks · Video

Official

Text-to-video with synchronized audio. Generates a soundtrack alongside the picture and returns a single MP4 with both tracks.

Wan2.2-S2V-14B (Presenter / Talking Head)Alibaba · Video

Official

Speech-to-video: animates a portrait to speak driving audio.

Fun-ASR-NanoAlibaba · Speech-to-text

Official

LLM-Powered Speech Recognition — 31 Languages, Dialects & Accents End-to-end ASR trained on tens of millions of hours of data. Supports Chinese (+ dialects), English, Japanese, Korean, French, German, Spanish, and 24 more languages.

Qwen3-ASR-1.7BAlibaba · Speech-to-text

Official

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. Both leverage large-scale speech training data and the strong audio understanding capability of their foundation model, Qwen3-Omni. Experiments show that the 1.7B version achieves state-of-the-art performance among open-source ASR models and is competitive with the strongest proprietary commercial APIs.

Whisper-Large-V3-TurboOpenAI · Speech-to-text

Official

Whisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3. In other words, it's the exact same model, except that the number of decoding layers have reduced from 32 to 4. As a result, the model is way faster, at the expense of a minor quality degradation.

Kokoro-82MKokoro · Text-to-speech

Official

Fast, lightweight text-to-speech model

Qwen3-TTSAlibaba · Text-to-speech

Official

Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles to meet global application needs. In addition, the models feature strong contextual understanding, enabling adaptive control of tone, speaking rate, and emotional expression based on instructions and text semantics, and they show markedly improved robustness to noisy input text.

ViiTorVoice-NAR is a non-autoregressive speech generation model for voice cloning, local speech editing, and emotion / paralinguistic speech control.

pyannote Speaker Diarization 3.1pyannote · Diarization

Official

Speaker diarization — detects who spoke when. Returns speaker turns with start/end times; pair with a transcription model for labelled transcripts.

Stable Audio Open 1.0Stability AI · Music & audio

Official

Text to audio — music beds and sound effects, 44.1kHz stereo, up to 47 seconds.

Jina-Embeddings-V3Jina AI · Embedding

Official

jina-embeddings-v3 is a multilingual multi-task text embedding model designed for a variety of NLP applications. Based on the Jina-XLM-RoBERTa architecture, this model supports Rotary Position Embeddings to handle long input sequences up to 8192 tokens.

Jina-Embeddings-V4Jina AI · Embedding

Official

jina-embeddings-v4 is a universal embedding model for multimodal and multilingual retrieval. The model is specially designed for complex document retrieval, including visually rich documents with charts, tables, and illustrations.

qwen3-embedding-0.6bAlibaba · Embedding

Official

Qwen3-Embedding-0.6B has the following features: Model Type: Text Embedding Supported Languages: 100+ Languages Number of Parameters: 0.6B Context Length: 32k Embedding Dimension: Up to 1024, supports user-defined output dimensions ranging from 32 to 1024

BGE-Reranker-V2-M3BAAI · Reranker

Official

bge-reranker-v2-m3，Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.