Search the full model catalog.

xAI’s Grok Imagine Image generates images from prompts and can edit a source image using instructions. Pick an aspect ratio, 1K or 2K, and 1–10 samples.

Edit or extend a short clip with xAI Grok Imagine. Upload a source video and a detailed prompt to generate a continued MP4 sequence.

Create short cinematic videos from a text prompt, guided by up to 16 reference images for consistent style and subjects. Built by xAI.

OmniVoice by k2-fsa generates 24 kHz speech from text in 600+ languages. Clone a speaker from a short reference clip or design a new voice from attributes.

Generate videos from text prompts using Alibaba's WAN 2.7 model. Supports both text-to-video and image-to-video conversion with customizable duration and resolution.

Grok Imagine Video by xAI generates short MP4 videos with synced audio from a text prompt, with an optional first-frame image. Choose duration, aspect, and 480p or 720p.

Decensored Qwen3.5-4B checkpoint for chat, coding, and analysis. Supports optional thinking traces and sampling controls for output style. On Wiro a request takes about 72K input tokens and returns up to 16K.

A large language model optimized for chat interactions and logical reasoning tasks. Designed for developers and researchers.

A compact yet capable LLM optimized for chat interactions and logical reasoning tasks. Designed for efficient deployment and accurate responses.

Generate or edit images using text prompts or image edits with GPT Image 1.5. Supports multiple sizes, formats, and quality settings.

A dense 9-billion parameter language model optimized for chat and reasoning tasks. Designed for efficient deployment and high-quality responses.

CohereLabs cohere-transcribe-03-2026 is a 2B Conformer speech-to-text model for 14 languages. It creates accurate transcripts for meetings, calls, and audio archives.

A large language model optimized for chat interactions and reasoning tasks, designed for advanced users seeking powerful natural language processing capabilities.

Generate stylish Instagram-style pose images with trendy angles, natural expressions, and a modern aesthetic. Built by Wiro for social content.

Song Generation 2 generates full songs with vocals and instrumentals from lyrics — supports 14 genres, reference audio cloning, and separate track output (vocal/bgm/mix).

TADA is a unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment. By leveraging a novel tokenizer and architectural design, TADA achieves high-fidelity synthesis and generation with a fraction of the computational overhead required by traditional models.

Generate high-resolution images using Seedream v4.5 Uncensored. Supports text-to-image and image-to-image transformations with customizable settings.

It turns any video into a cinematic experience by generating AI-powered instrumental soundtracks that match its mood.

ACE-Step v1.5 is a highly efficient open-source music foundation model designed to bring commercial-grade music generation to consumer hardware.

A lightweight language model optimized for efficient inference and versatile applications in natural language processing tasks.