Try MiniMax FastH3 V2 from Fastvideo →

Pricing Blog Docs

ExploreDiscover models by category Browse All ModelsBrowse the complete catalog See FavoritesSign in to view saved models

Generative Media AgentCreate and edit media by chatting Workflow AgentBuild visual workflows with Agent

OverviewThe platform at a glance LearnSkills, knowledge, guardrails AnatomyWhat makes agents reason Build Your AgentPick skills, set tier, deploy

Pre-built AgentsBrowse the catalog

Agent Usecases

Ad Campaign Manager App Event Manager App Review Replies Barber Booking Customer Win-Back Ecommerce Listings Restaurant Reviews

Sign In Start Building

Task History

Click to see output list

No tasks yet

Discover AI models

Search the full model catalog.

Discover and compare production-ready models. Filter by modality, provider, pricing, and production fit.

523 models0 active filters

Wiro AI

Video Generation

Image Generation

Audio & Speech

Realtime Stream

Music Generation

3D Generation

LLM & Chat

Workflow

Partners

Need help choosing?

Compare models by capability, cost, and provider fit.

Showing 20 of 523 models

Sort by

Fast-H3-V2

FastH3 V2 is an eight-forward distilled MiniMax H3 model that generates synchronized video and stereo audio from a text prompt. This H200-backed 8-step checkpoint supports native 5.167-14.375 second T2AV clips at 24 FPS; FL2VA and Ref2VA were not distilled.

Text to Videotext-to-videoaudio-video

wan 3.0 prime pro r2v uncensored

Create 2–30s reference-guided videos from a prompt plus up to 10 images, 5 clips, and 5 audio tracks. Export 1080p, 2K, or 4K MP4.

wan 3.0 prime pro uncensored

Generate 5–30 second videos from a written shot prompt, with optional first and last frame keyframes, audio on/off, and 1080p to 4K output.

wan 3.0 prime r2v uncensored

Generate 2–30s 480p–1080p MP4 videos from a prompt plus up to 10 reference images, with optional reference video and audio for stronger identity control.

wan 3.0 prime uncensored

Create 5–30s MP4 videos from a prompt, optionally anchored by first and last frame images with optional audio. Powered by Alibaba Wan 3.0 Prime.

wan 3.0 pro r2v uncensored

Generate uncensored reference-to-video clips with Wan 3.0 Pro R2V. Add up to 10 images plus optional video and audio references, and export 1080p–4K MP4.

wan 3.0 pro uncensored

Create 5–30s cinematic video from one prompt, with optional first and last frame anchors, 1080p–4K output tiers, and an audio track toggle.

wan 3.0 r2v uncensored

Generate 2–30s reference-guided videos from a prompt plus optional images, clips, and audio. This R2V build targets strong identity and style consistency.

wan 3.0 uncensored

Generate 5–30s MP4 videos from a prompt, with optional first and last frame images. Pick 480p–1080p resolution, aspect ratio, and audio.

wan 2.7 uncensored

Animate a still image into a 5–15s HD video from your motion prompt, with optional negative prompts, audio control, and reproducible seeds.

wan 3.0 prime r2v

Wan 3.0 Prime R2V by Alibaba generates 2–30s MP4 videos from prompts plus reference images, clips, and audio for consistent identity and style.

wan 3.0 prime

Wan 3.0 Prime generates 5–30 second MP4 videos from a written prompt, with optional first and last frames. Pick 480p–1080p and an aspect ratio to shape the shot.

wan 3.0 r2v

Generate 2–30s MP4 videos from a prompt plus reference images, video, and audio. Wan 3.0 R2V helps keep subjects, motion, and style consistent.

wan 3.0

Wan 3.0 by Alibaba generates cinematic videos up to 30 seconds at 1080p. Start from text alone or lock the first and last frames for tighter control.

Push Yourself Effects

Transform a single portrait into a high-stakes cinematic adventure. Face frozen cliffs, desert canyons, volcanic edges, jungle temples, towering rooftops and breathtaking drops — with your face and identity preserved throughout.

qwen image max uncensored - AI model cover image

qwen image max uncensored

Qwen Image Max uncensored generates or edits images from instructions, with optional reference photos for stable identity, style transfer, and multi-image fusion.

wan 2.6 uncensored

Generate 5–15s 720p/1080p clips from a prompt, with optional first-frame image and audio. WAN 2.6 uncensored is tuned for bold motion and contrast.

p-video-2-pro

Generate 5–15 second videos from a prompt or first and last frame images. Choose Speed or Quality, and export 480p or 768p video at 24 fps with synced audio.

Car Transformation Effects

Transform a single car photo into a cinematic vehicle adventure. Turn your car into a powerful robot, a stylized cartoon character or place it inside an iconic open-world street scene — while preserving its recognizable design and details.

Self Training Season Effects

Transform a single portrait into a high-stakes cinematic rescue video. Face frozen wilderness, desert emergencies, collapsing bridges, flooded subways and burning corridors — with your face and identity preserved throughout.

Showing 20 of 523 models

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational

WiroAbout Blog Careers Contact

ProductModels Agents Pricing Partner Changelog Status FAQ

ModelsNano Banana 2 GPT Image 2.5 Seedream V5 Pro Seedance 2.5 Veo 3.1 Kling V3 FLUX 3 FLUX.2 Pro Wan 3.0 Prime Grok Imagine 1.5

PartnersGoogle OpenAI ByteDance Black Forest Labs Kling AI Qwen Alibaba xAI MiniMax ElevenLabs

Getting StartedIntroduction Authentication Projects Code Examples Wiro MCP Server Self-Hosted MCP n8n Integration LLMs.txt

API ReferenceModels Run a Model Model Parameters Tasks LLM & Chat Streaming WebSocket Realtime Voice Files

© 2026 Wiro AI. All rights reserved.

Privacy Terms Data Deletion