在 API 请求中，将
id 值用作 model 参数。当前有 60 个模型可用。生成
| Model | ID | Price | Privacy |
|---|---|---|---|
| Anime (WAI) | wai-Illustrious | $0.01 | Private |
| Background Remover | bria-bg-remover | $0.03 | Anonymized |
| Chroma | chroma | $0.01 | Private |
| Flux 2 Max | flux-2-max | $0.09 | Anonymized |
| Flux 2 Pro | flux-2-pro | $0.03 | Anonymized |
| GPT Image 1.5 | gpt-image-1-5 | $0.26 | Anonymized |
| GPT Image 2 | gpt-image-2 | 1K: 0.27,2K:0.51, 4K: $0.84 | Anonymized |
| Grok Imagine | grok-imagine-image | 1K: 0.03,2K:0.04 | Private |
| Grok Imagine 2.0 | grok-imagine-image-2-0 | 1K: 0.07,2K:0.10 | Private |
| Grok Imagine High Quality (SOTA) | grok-imagine-image-quality | 1K: 0.06,2K:0.09 | Private |
| Hunyuan Image 3.0 | hunyuan-image-v3 | $0.09 | Private |
| Ideogram V4 | ideogram-v4 | $0.06 | Anonymized |
| ImagineArt 1.5 Pro | imagineart-1.5-pro | $0.06 | Anonymized |
| Krea 2 Turbo | krea-2-turbo | 1K: 0.04,2K:0.06 | Private |
| Krea v2 Large | krea-v2-large | $0.07 | Anonymized |
| Krea v2 Medium | krea-v2-medium | $0.04 | Anonymized |
| Luma Uni-1 | luma-uni-1 | $0.05 | Anonymized |
| Luma Uni-1 Max | luma-uni-1-max | $0.12 | Anonymized |
| Lustify SDXL | lustify-sdxl | $0.01 | Private |
| Lustify v7 | lustify-v7 | $0.01 | Private |
| Lustify v8 | lustify-v8 | $0.01 | Private |
| Nano Banana 2 | nano-banana-2 | 1K: 0.10,2K:0.14, 4K: $0.19 | Anonymized |
| Nano Banana 2 Lite | nano-banana-2-lite | $0.06 | Anonymized |
| Nano Banana Pro | nano-banana-pro | 1K: 0.18,2K:0.23, 4K: $0.35 | Anonymized |
| Qwen Image | qwen-image | $0.03 | Anonymized |
| Qwen Image 2 | qwen-image-2 | $0.05 | Anonymized |
| Qwen Image 2 Pro | qwen-image-2-pro | $0.10 | Anonymized |
| Qwen Image 3 | qwen-image-3 | 1K: 0.04,2K:0.04 | Anonymized |
| Qwen Image 3 Pro | qwen-image-3-pro | 1K: 0.05,2K:0.09 | Anonymized |
| Recraft V4 | recraft-v4 | $0.05 | Anonymized |
| Recraft V4 Pro | recraft-v4-pro | $0.29 | Anonymized |
| Seedream V4.5 | seedream-v4 | $0.05 | Anonymized |
| Seedream V5 Lite | seedream-v5-lite | $0.05 | Anonymized |
| Seedream V5 Pro | seedream-v5-pro | 1K: 0.06,2K:0.11 | Anonymized |
| Venice SD35 | venice-sd35 | $0.01 | Private |
| Wan 2.7 | wan-2-7-text-to-image | $0.04 | Anonymized |
| Wan 2.7 Pro | wan-2-7-pro-text-to-image | $0.09 | Anonymized |
| Z-Image Turbo | z-image-turbo | $0.01 | Private |
放大
| Model | ID | Price | Privacy |
|---|---|---|---|
| Upscaler | upscaler | 2x 0.02,4x0.08 | Private |
编辑
| Model | ID | Price | Privacy |
|---|---|---|---|
| FireRed Edit | firered-image-edit | $0.04 | Private |
| Flux 2 Max | flux-2-max-edit | 0.12/额外图像0.03 | Anonymized |
| GPT Image 1.5 | gpt-image-1-5-edit | 0.31/额外图像0.03 | Anonymized |
| GPT Image 2 | gpt-image-2-edit | 0.34/额外图像0.0092 | Anonymized |
| Grok Imagine | grok-imagine-edit | 0.03/额外图像0.0023 | Private |
| Grok Imagine 2.0 | grok-imagine-image-2-0-edit | 0.07/额外图像0.01 | Private |
| Grok Imagine High Quality | grok-imagine-quality-edit | 0.06/额外图像0.01 | Private |
| Luma Uni-1 | luma-uni-1-edit | $0.06 | Anonymized |
| Luma Uni-1 Max | luma-uni-1-max-edit | $0.13 | Anonymized |
| Nano Banana 2 | nano-banana-2-edit | $0.10 | Anonymized |
| Nano Banana 2 Lite | nano-banana-2-lite-edit | $0.06 | Anonymized |
| Nano Banana Pro | nano-banana-pro-edit | $0.18 | Anonymized |
| Qwen Edit Uncensored | qwen-edit-uncensored | $0.04 | Private |
| Qwen Image 2 | qwen-image-2-edit | $0.05 | Anonymized |
| Qwen Image 2 Pro | qwen-image-2-pro-edit | $0.10 | Anonymized |
| Qwen Image 3 Edit | qwen-image-3-edit | 0.04/额外图像0.0035 | Anonymized |
| Qwen Image 3 Pro Edit | qwen-image-3-pro-edit | 0.05/额外图像0.0035 | Anonymized |
| Seedream V4.5 | seedream-v4-edit | $0.05 | Anonymized |
| Seedream V5 Lite | seedream-v5-lite-edit | $0.05 | Anonymized |
| Seedream V5 Pro | seedream-v5-pro-edit | 0.06/额外图像0.0035 | Anonymized |
| Wan 2.7 Pro Edit | wan-2-7-pro-edit | $0.09 | Anonymized |
模型类型
- 生成： 根据文本提示创建图像
- 放大： 提升图像分辨率和质量
- 编辑： 通过 inpainting 修改现有图像
请参阅 Image Generate API 进行文生图，Upscale API 进行增强，以及 Edit API 进行 inpainting。
图像生成尺寸是模型专属的。基于像素的模型（如
venice-sd35 和 qwen-image）使用 width 和 height；基于宽高比的模型（如 qwen-image-2）使用 aspect_ratio；列出了 1K、2K 或 4K 等分辨率选项的模型则同时使用 resolution 和 aspect_ratio。