Models Overview
Current pricing is maintained on the main site:
Image Generation
Section titled “Image Generation”| Model | Provider | Primary Endpoint | Best For |
|---|---|---|---|
| Nano Banana | /v1/chat/completions | Fast iteration, conversational image generation | |
| Nano Banana 2 | /v1/chat/completions | Balanced quality, speed, and production throughput | |
| Nano Banana Pro | /v1/chat/completions | Premium brand visuals and higher-resolution output | |
| GPT Image 1.5 | OpenAI | /v1/images/generations | Text rendering, layout-heavy assets |
| GPT Image 2 | OpenAI | /v1/chat/completions | Prompt-heavy chat-compatible image workflows |
| GPT Image 2 Beta | OpenAI | /v1/images/generations | Preview testing and model comparisons |
| FLUX 1.1 Pro | Black Forest Labs | /v1/images/generations | Photorealistic ads and product visuals |
| Qwen Image 2.0 | Alibaba | /v1/images/generations | Chinese text rendering, cost-aware image generation |
Video Generation
Section titled “Video Generation”| Model | Provider | Primary Endpoint | Best For |
|---|---|---|---|
| HappyHorse 1.0 | Alibaba | /v1/videos | Short-form, ad storyboards, and social media clips |
| Kling 3.0 | Kuaishou | /v1/videos | Cinematic motion and action-heavy clips |
| Seedance 1.0 Pro | ByteDance | /v1/videos | Cost-aware batch video generation and fast prototypes |
| Seedance 1.5 Pro | ByteDance | /v1/videos | Narrative 1080P videos with native audio |
| Seedance 2.0 | ByteDance | /v1/videos | Unified text-to-video and image-to-video workflows |
| Wan 2.7 T2V | Alibaba | /v1/videos | General text-to-video generation |
| Wan 2.7 I2V | Alibaba | /v1/videos | Turning still images into animated clips |