AI Model Catalog

DeepSeek R1 is a reasoning model family for tasks such as coding, analysis and mathematics. The catalog includes several model sizes; compare their GP...

Qwen3 is a language model family from Alibaba Cloud with thinking and non-thinking modes. Use it for multilingual chat, document analysis and coding; ...

Qwen3.5 is a language model family from Alibaba Cloud with thinking and non-thinking modes. The catalog includes dense and mixture-of-experts variants...

QwQ is a 32B reasoning model from Alibaba for mathematics, programming and logic tasks. Review generated answers before relying on them.

LLaMA 4 is an open-weight model family from Meta. Scout uses a mixture-of-experts architecture and supports multimodal inputs. This catalog also inclu...

Mistral AI develops language models for chat, document processing and structured text generation. This catalog includes Ministral 8B and Mistral Nemo ...

GPT-OSS is OpenAI’s open-weight model family, available here in 20B and 120B configurations. It supports reasoning and tool-use applications; integrat...

Gemma 3 is Google’s model family for instruction following and language tasks. The catalog offers 4B, 12B and 27B configurations with different GPU re...

Phi-4 is Microsoft’s 14B language model for tasks such as coding, mathematics and text reasoning. Review the recommended GPU and test representative p...

GLM models from Zhipu AI support Chinese and English language tasks. GLM-Z1 variants add reasoning capabilities. Compare the available sizes and check...

Magistral is a 24B reasoning model from Mistral AI. It can help draft analyses and summarize documents; its outputs require review, especially for leg...

Qwen-Image-2512 is an image generation model from Alibaba’s Tongyi Lab. It supports workflows involving portraits, text in images and composed scenes....

Z Image Turbo is a distilled image generation model from Alibaba Tongyi. It can be used for image variations, prototyping and batch workflows. Generat...

Z-Anime is a SeeSee21 anime fine-tune of Z-Image built for fast stylized image generation. It uses natural-language prompting rather than booru tags a...

Flux is an image generation family from Black Forest Labs. The catalog includes Dev, four-step Schnell and Krea variants for text-to-image workflows. ...

Flux Kontext Dev is an image-editing model from Black Forest Labs that uses a reference image to guide changes and new scenes. Character identity and ...

Paid launch unavailable

FLUX.2 is Black Forest Labs’ image model family with multi-image editing support. The catalog includes full and quantized configurations with differen...

FLUX.2 Klein is an image generation family with 4B and 9B variants. The catalog includes a 9B FP8 configuration. Compare GPU requirements and the vari...

HiDream I1 is a 17B image generation model family. The catalog includes Dev, Full and Fast variants with FP8 configurations for text-to-image workflow...

Stable Diffusion is an image generation family from Stability AI with community fine-tunes and LoRAs. The catalog includes SDXL, SD 3.5 and SD 1.5 con...

Qwen Image models from Alibaba Tongyi support image generation and text-guided editing, including Chinese and English prompts. Review text, compositio...

LTX-2.3 is a 22B video model from Lightricks with synchronized audio generation. The catalog offers distilled and FP8 configurations. Resolution, fram...

Wan 2.2 is Alibaba Tongyi Lab's video generation family. The dense 5B variant is the lighter option, while the 14B mixture-of-experts variants target ...

HunyuanVideo 1.5 is Tencent's flagship video generation model with 8.3B parameters. It supports both text-to-video and image-to-video workflows, runni...

LTX-2 from Lightricks is a 19B video model with audio support. The catalog includes an eight-step distilled configuration and quantized dev variants. ...

Wan 2.1 is an earlier generation of Alibaba’s video models. These 14B configurations support text-to-video and image-to-video workflows, including pro...

Kokoro is an 82M text-to-speech model with multiple built-in voices and multilingual support. Use it for narration and speech applications; audition p...

Chatterbox from Resemble AI supports text-to-speech and voice cloning. Turbo supports paralinguistic tags, while Standard includes emotion controls. A...

ComfyUI Audio Suite combines F5-TTS, Chatterbox, Kokoro, and Qwen3-TTS engines in a visual workflow canvas. Build complex audio pipelines with voice c...