6. Models
AI models available across Mosaic features.
Mosaic uses a range of AI models across its creation tiles. Video and audio models are billed by generation duration. Image models are billed by generated image and selected quality or resolution. One subscription gives you access to all models.
AI Avatar
Generate realistic AI presenters that speak your script with natural lip sync. Learn more
| Model | Unit |
|---|---|
| Seedance 2 Fast | Generation Seconds |
| Seedance 2 | Generation Seconds |
| Kling 2.6 Pro | Generation Seconds |
| Kling 3 | Generation Seconds |
| Kling 3 Pro | Generation Seconds |
AI Avatar (Single Take)
Create single-take avatar videos with a continuous, natural delivery style. Learn more
| Model | Unit |
|---|---|
| Fabric 1 | Generation Seconds |
| Longcat 1 | Generation Seconds |
Video Generation
Generate video clips from text prompts and optional media references. Learn more
| Model | Unit |
|---|---|
| Seedance 2 | Generation Seconds |
| Seedance 2.5 | Generation Seconds |
| Gemini Omni Flash | Generation Seconds |
INFO
Seedance 2 output at 4K resolution is billed at 2x normal Seedance. Gemini Omni Flash supports prompt-only generation, selected images, or one selected video using the first 10 seconds.
Audio Generation
Generate voiceovers or music from scripts and prompts. Learn more
| Model | Unit |
|---|---|
| Eleven v3 | Generation Seconds |
| Music | Generation Seconds |
Image Generation
Generate still images from prompts and image context. Learn more
| Model | Unit |
|---|---|
| Nano Banana Lite | Generated Images |
| Nano Banana | Generated Images |
| Nano Banana Pro | Generated Images |
| GPT Image 2 | Generated Images |
TIP
Credits are consumed based on the model, generation duration, and image quality or resolution. Check your usage anytime in Settings > Usage. View usage