Search the full model catalog.

Z-Image is a powerful and highly efficient image generation model.

Moondream3 is a cutting-edge vision-language model that delivers advanced visual reasoning with built-in object detection, pointing, and OCR capabilities—bringing fast, cost-effective, and scalable inference to real-world applications.

Name an object and Moondream 3 Preview returns one normalized x, y point for each match, as JSON you can count or draw as markers on the image.

Moondream 3 Preview writes a prose caption for an image. There is no prompt: you choose Short, Normal or Long and the model decides what to describe.

Ask Moondream 3 Preview a question about one image and get the answer as text or JSON. A reasoning step runs by default and can be switched off for simple questions.

OpenAI's smaller open-weight reasoning model, a mixture-of-experts with 21B parameters (3.6B active) under Apache 2.0, served here as a text chat model with per-session history.

A Qwen3 mixture-of-experts model (30.5B total, 3.3B active) that reasons in a think block or answers directly, chosen turn by turn. On Wiro it accepts function definitions and can return JSON.

Qwen3-30B-A3B-Thinking-2507 reasons before every answer, and its thinking runs longer than in the original Qwen3-30B-A3B. Qwen recommends it for highly complex reasoning tasks.

Qwen3-32B is Qwen's 32.8B dense model. It reasons step by step by default and answers directly on request, and on Wiro it can call your functions or return a JSON object.

A Qwen3-Coder model for agentic coding and everyday programming that activates 3.3B of its 30.5B parameters per token. It runs in non-thinking mode only, so each reply starts with the answer.

Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning.

Puts one or two faces into a scene it generates from your prompt, or into a photo you upload. In a two-person photo it can replace just the left or the right person.

Mixed dataset LLM Information Security v1.5 - Incident Response v1.3.1 - Threat Hunting v1.3.2 - Ethical Exploit Development v2.0 - Purple Team Tactics v1.3 - Reverse Engineering v2.0

Trains a FLUX.1 [dev] LoRA on photos of one person. Captioning and the training recipe are fixed for portraits; you choose the trigger word, step count and learning rate.

SkyReels V1 is the first and most advanced open-source human-centric video model.

DeepSeek's mixture-of-experts vision-language model, run here as the Tiny checkpoint. Give it one image and a question and it answers in plain text, from a full caption to a one-line note on what looks odd.

NSFW video detection automatically analyzes video content to identify inappropriate or explicit material, ensuring compliance with content policies and a safe viewing environment.

Stability AI's 8.1B-parameter MMDiT text-to-image model from the Stable Diffusion 3.5 release, built for 1 megapixel images in styles that range from photography and 3D to painting and line art.

DAMO-NLP-SG's 2B VideoLLaMA 3 model watches a video clip and answers in English text. It skips image patches that stay the same from frame to frame, so static shots use fewer tokens.

The 2B image checkpoint of DAMO-NLP-SG's VideoLLaMA 3 answers questions about a picture in English. Larger images get more vision tokens, which helps with small print in documents and charts.