The model library
AI video models, all in one place
The new Seedance 2.5, plus Veo, Kling, Wan and Happy Horse — the leading AI video models, online on OpenGradient with one prompt box and per-clip pricing. No apps, no API keys, no subscriptions. Pick a model to see what it's best at.
Free credits to start · no card · switch models any time
Seedance 2.5New
by ByteDance
Newest Seedance: top quality and motion, clips up to 30s with synced audio.
- Text & image to video
- Clips up to 30s
- Synced audio & dialogue
Seedance 2.0Great Quality
by ByteDance
Best overall quality and motion with synced audio.
- Text & image to video
- Clips up to 15s
- Synced audio & dialogue
Wan 2.7Uncensored
by Alibaba
Newest Wan, with audio. Unfiltered.
- Text & image to video
- Clips up to 10s
- No content filters (18+ gate)
Happy Horse 1.1Most Uncensored
by Alibaba
The most uncensored model - zero filters. Widescreen 21:9 support.
- Text & image to video
- Clips up to 10s
- No content filters (18+ gate)
Veo 3.14K
by Google
Google's flagship: top realism and physics, audio, up to 4K. Filtered.
- Text & image to video
- Clips up to 8s
- Native audio
Kling v3 ProHi-Fi
by Kling AI
Sharp detail and fluid motion with audio, up to 15s. Filtered.
- Text & image to video
- Clips up to 15s
- Audio with video
Nano Banana 2
by Gemini · Latest, highest quality
~71 credits per image
GPT Image 2
by OpenAI · OpenAI's high-fidelity image model
53 credits per image
Seedream 5.0 LiteUncensored
by ByteDance · Newest Seedream — fast, high-resolution images
37 credits per image
Seedream 4.5Uncensored
by ByteDance · High-resolution cinematic image generation
53 credits per image
Seedream 5.0Uncensored
by ByteDance · Newest flagship Seedream — highest quality
95 credits per image
GLM-Image
by Z.ai · Low-cost image generation
16 credits per image
All of them live in one studio — generate, compare and edit with the same prompt box.
Claude Haiku 4.5
by Anthropic · Fast, low-cost replies for everyday tasks
Claude Sonnet 5
by Anthropic · Balanced all-rounder for writing and code
Claude Opus 5
by Anthropic · Latest Opus — top-tier reasoning for complex work
Claude Fable 5
by Anthropic · Anthropic's most capable model for demanding work
GPT-4.1 Nano
by OpenAI · Cheapest option for simple tasks
GPT-5 Mini
by OpenAI · Fast and affordable for daily use
GPT-5
by OpenAI · Powerful all-rounder, previous generation
GPT-5.6 Luna
by OpenAI · Latest GPT model for fast everyday work
GPT-5.6 Terra
by OpenAI · Latest GPT model with strong reasoning at balanced cost
GPT-5.6 Sol
by OpenAI · Most capable latest GPT model
Gemini 2.5 Flash Lite
by Google · Cheapest for high-volume tasks
Gemini 2.5 Pro
by Google · Deep reasoning with a huge context window
Gemini 3.6 Flash
by Google · Latest Gemini for agentic and multimodal work
Gemini 3.5 Flash Lite
by Google · Low-cost Gemini for fast, high-volume tasks
Grok 4.5
by xAI · Latest Grok with strong reasoning and live web awareness
Grok 4 Fast
by xAI · Quick answers at low cost
Grok 4
by xAI · Solid all-around performance
Grok 4.3
by xAI · Latest Grok - top-tier reasoning and capability
DeepSeek V4 Flash
by DeepSeek · Fast, low-cost DeepSeek model
DeepSeek V4 ProUncensored
by DeepSeek · Deep reasoning model with a 1024K context window
Seed 2.0 Lite
by ByteDance · Lightweight and budget-friendly
Seed 1.6
by ByteDance · Balanced choice for everyday use
Seed 1.8
by ByteDance · Most capable Seed model, strong multilingual
Hermes 4 70BUncensored
by Nous Research · Fast, low-cost open-weight assistant
Hermes 4 405BUncensored
by Nous Research · Flagship Hermes — strong reasoning, steerable and uncensored
GLM-5.2
by Z.ai · Z.ai flagship reasoning model with lower cost than Opus
Every one of them behind the same private prompt box — switch mid-conversation any time.
Not sure which model? Just start.
Every model here shares one prompt box — run the same idea on two or three of them for cents and keep the winner.