AI Video & Image Models
One page per model. Real pricing, real capabilities, no marketing fluff. Use this as the index for everything Slates supports plus the models worth knowing about even if we don't run them yet.
Seedance 2.0: ByteDance's Audio-First AI Video Model
→Seedance 2.0 is ByteDance's AI video model. It generates 4 to 15 second clips at 720p with synced audio baked into the same generation pass. Raw API pricing starts at $0.108 per second on the Economy tier and $0.2419 per second on Priority, both far cheaper than CapCut Pro's monthly subscription markup. Slates ships both tiers with credit-based pricing, plus your own fal.ai API key for the Priority tier on Slates Pro.
Kling AI: The Camera-Control King of AI Video
→Kling AI is Kuaishou's video generation model and the most camera-aware AI video tool on the market. V3 Standard runs at $0.084 per second, V3 Pro at $0.112 per second, and V3 Omni at $0.084 per second with audio included. All three tiers support 15 second clips and 6-axis camera controls without any subscription.
Google Veo 3 / Veo 3.1: The Only Native 4K AI Video Model
→Veo 3 (officially Veo 3.1) is Google's flagship AI video generation model. It's the only mainstream AI video model that outputs native 4K. Raw API pricing starts at $0.10 per second for the Fast tier without audio and runs up to $0.60 per second for Standard 4K with audio. Slates ships it with credit-based pricing, and Slates Pro users can plug in their own Google API key to pay raw rates directly.
Nano Banana 2: Google's Fast, Cheap Image Generation Model
→Nano Banana 2 is Google's image generation model. The technical name is Gemini 3.1 Flash Image. It replaced the previous Nano Banana Pro on February 26, 2026, and runs about 50% cheaper at $0.067 per image at 1K resolution. It's built on the Gemini Flash architecture, so generation latency is sub-500ms.
Seedream 5 Lite: ByteDance's Uncensored Image Model
→Seedream 5 Lite is ByteDance's image generation and editing model. It's the uncensored fast-and-cheap option in most workflows, with strong face consistency and the ability to reference up to 10 images per edit. It ships in Slates on credit-based pricing and is the default fallback when Nano Banana 2 rejects a prompt.
Sora 2: What It Is, What It Costs, and What To Use If You Can't Get It
→Sora 2 is OpenAI's text-to-video model, released September 30, 2025. It generates 5 to 15 second clips at 720p with native synced audio. Access runs through ChatGPT Plus ($20/mo) or ChatGPT Pro ($200/mo for Sora 2 Pro and 1080p). For the same audio-first use case without the subscription lock, Seedance 2.0 on Slates covers comparable quality at similar per-second cost.