API 更新
新增模型、功能与改进的更新记录。
pixverse-v6-max
> 🚀 新品上线 > > 视频生成模型
PixVerse V6 Max现已正式登陆 AiBox。✨ 核心亮点
| 能力 | 说明 | | --- | --- | | 生成模式 | 文生视频、单图生视频 | | 输出规格 | 360p / 540p / 720p / 1080p | | 画面比例 | 文生支持 16:9、9:16、4:3、3:4、1:1、2:3、3:2、21:9;图生跟随参考图片比例 | | 视频时长 | 1~15 秒,支持按整数秒设置 | | 音频生成 | 可选原生音轨,默认无声 |
输出采用上游原生尺寸,以实际返回为准。
🎯 适用场景
- 营销素材与产品展示
- 商品图片动态化
- 社交媒体短视频
- 创意原型快速制作
📚 [查看 PixVerse V6 Max API 文档](https://aiboxapi.com/en/api-reference/videos/pixverse-v6-max/generation)
kling-4-0
> 🚀 新品上线 > > 视频生成模型 Kling 4.0(
kling-v4)现已正式登陆 AiBox。✨ 核心亮点
| 能力 | 说明 | | --- | --- | | 生成模式 | 文生视频、图生视频、多模态参考、视频编辑、视频续写 | | 输出规格 | 720p / 1080p | | 画面比例 | 16:9、9:16、1:1、21:9;参考模式支持自动适配,续写沿用原视频比例 | | 视频时长 | 3~30 秒,按整数秒调节;续写时指定新增片段时长 | | 关键帧控制 | 图生视频支持首帧、可选尾帧及最多 8 张中间帧 | | 音频输出 | 视频始终带立体声音轨 |
🎯 适用场景
- 营销素材与产品动态展示
- 社交媒体短视频与创意内容制作
- 分镜预演、视频改编与片段续写
📚 [查看 Kling 4.0 API 文档](https://aiboxapi.com/api-reference/videos/kling-v4/generation)
hy-image-v3.5-preview
> 🚀 新品上线 > > 腾讯混元图像生成模型
hy-image-v3.5-preview(HY Image 3.5 Preview)现已正式登陆 AiBox。✨ 核心亮点
| 能力 | 说明 | | --- | --- | | 生成模式 | 文生图、参考图生图(最多 5 张) | | 输出规格 | 1K / 2K / 4K 三档,也可自定义精确像素(单边 256–8192,最高约 830 万像素) | | 画面比例 | 1:1、2:3、3:2、3:4、4:3、4:5、5:4、9:16、16:9、21:9,另支持 auto | | 提示词 | 中英文均可,支持负面提示词排除不想要的内容 | | 结果复现 | 支持固定 seed | | 计费方式 | 按张计费,按输出档位收费,生成失败全额退款 |
🎯 适用场景
- 电商主图与营销海报设计
- 社交媒体配图与内容创作
- 基于参考图的风格延展与二次创作
- 横幅、壁纸等指定尺寸的出图需求
📚 [查看 HY Image 3.5 Preview API 文档](https://aiboxapi.com/en/api-reference/images/hy-image-v3.5-preview/generation)
flux-3-image-klein
> 🚀 新品上线 > > 图像生成模型
flux-3-image-klein(FLUX 3 Image Klein)现已正式登陆 AiBox。✨ 核心亮点
| 能力 | 说明 | | --- | --- | | 生成模式 | 文生图、单图编辑、多图参考(最多 10 张) | | 输出规格 | 768SQ / 1K / 1.5K / 2K / 4K(最高约 16MP) | | 画面比例 | 21:9 至 9:21 共 15 种比例,另支持 auto | | 推理步数 | 1–16 步可调,默认 16 步,步数少出图更快 | | 输出格式 | JPEG / PNG | | 计费方式 | 按张计费,只看分辨率,文生图与编辑同价 |
🎯 适用场景
- 电商商品图与营销素材批量生成
- 社交媒体配图与内容创作
- 基于参考图的图片编辑与多图融合
- 低成本快速出图与创意迭代
📚 [查看 FLUX 3 Image Klein API 文档](https://aiboxapi.com/en/api-reference/images/flux-3-image-klein/generation)
Vidu-q4-Preview
> 🚀 新品上线 > > 视频生成模型
Vidu Q4 Preview现已正式登陆 AiBox。✨ 核心亮点
| 能力 | 说明 | | --- | --- | | 生成模式 | 图生视频、参考生视频 | | 输出规格 | 540p / 720p / 1080p / 2K / 4K | | 画面比例 | 参考生支持 1:1、9:16、16:9、3:4、4:3;图生跟随首帧比例 | | 视频时长 | 3–16 秒,支持整数秒设置 | | 参考素材 | 参考生支持 1–15 张图片,最多搭配 3 段 MP3 音频 | | 音频生成 | 默认生成音轨,也可选择无声输出 |
🎯 适用场景
- 营销素材与产品动态展示
- 人物、场景与音频参考创作
- 社交媒体短视频与创意分镜制作
📚 [查看 Vidu Q4 Preview API 文档](https://aiboxapi.com/cn/api-reference/videos/vidu-q4-preview/generation)
mai-image-2.6
> 🚀 新品上线 > > 图像生成模型
mai-image-2.6(高质量版)与mai-image-2.6-flash(快速版)现已正式登陆 AiBox。✨ 核心亮点
| 能力 | 说明 | | --- | --- | | 生成模式 | 文生图、单图编辑、多参考图合成(最多 5 张参考图) | | 输出规格 | 文生图支持 1K / 2K,每次输出 1 张 PNG 图片 | | 画面比例 | 文生图支持 1:4~4:1 范围内的整数比,也可自动选择比例或指定像素尺寸 | | 联网增强 | 可开启 Bing 搜索,在生成前获取真实人物、地点与事件的相关信息 |
注:参考图编辑的输出尺寸与比例由模型根据参考图决定。
🎯 适用场景
- 营销海报与社交媒体配图
- 电商商品图与品牌视觉制作
- 参考图编辑与多图创意合成
📚 [查看 MAI-Image-2.6 API 文档](https://aiboxapi.com/cn/api-reference/images/mai-image-2.6/generation)
flux-3-image
> 🚀 新品上线 > > 图像生成与编辑模型
flux-3-image现已正式登陆 AiBox。✨ 核心亮点
| 能力 | 说明 | | --- | --- | | 生成模式 | 文生图、单图编辑、多图参考(最多 10 张参考图) | | 输出规格 | 768SQ / 1K / 1.5K / 2K / 4K | | 画面比例 | 支持 15 种比例,涵盖 1:1、16:9、9:16、21:9 等,并支持自动适配 | | 创作增强 | 网页与图片搜索增强,可通过提示词描述布局及局部编辑要求 |
🎯 适用场景
- 电商商品图与营销素材制作
- 社交媒体配图与多画幅视觉设计
- 多图参考创作与局部修改
📚 [查看 FLUX 3 Image API 文档](https://aiboxapi.com/cn/api-reference/images/flux-3-image/generation)
nano-banana-2-1
> 🚀 新品上线 > > 图像生成与编辑模型
Gemini Nano Banana 2.1现已正式登陆 AiBox,支持官方版与 Ext 版。✨ 核心亮点
| 能力 | 说明 | | --- | --- | | 生成模式 | 文生图、图生图、参考图编辑 | | 输出规格 | 1K / 2K / 4K | | 画面比例 | 1:1、16:9、9:16 等 10 种比例,支持自动模式 | | 出图数量 | 官方版单次 1–4 张,Ext 版单次 1 张 | | 计费方式 | 官方版按 Token 计费,Ext 版按张与分辨率计费 |
🎯 适用场景
- 电商商品图与营销海报
- 社交媒体视觉素材
- 参考图编辑与创意设计
📚 [查看 Gemini Nano Banana 2.1 API 文档](https://aiboxapi.com/cn/api-reference/images/gemini-nano-banana-2.1/generation)
Seedream-5.0-Flash
> 🚀 新品上线 > > 图像生成模型
Seedream-5.0-Flash现已正式登陆 AiBox。✨ 核心亮点
| 能力 | 说明 | | --- | --- | | 生成模式 | 文生图、图生图、多参考图融合 | | 输出规格 | 1K / 1.5K / 2K,支持自定义像素尺寸 | | 参考图输入 | 最多支持 10 张参考图 | | 交互编辑 | 支持坐标定位与手绘标记,指定编辑区域 | | 图层拆分 | 将图片拆分为底图与透明图层 | | 输出格式 | JPEG / PNG,支持透明背景 |
🎯 适用场景
- 营销海报与社交媒体配图
- 商品图片编辑与多图融合
- 局部修改与创意设计迭代
- 设计素材拆层与二次创作
📚 [查看 Seedream-5.0-Flash API 文档](https://aiboxapi.com/en/api-reference/images/seedream-5-0-flash/generation)
wan3.0-video-prime
🚀 新品上线
wan3.0-video-prime现已登陆 AiBox,支持通用视频生成、首尾帧视频生成,以及文件/网页转视频,并集成音频生成能力。✨ 核心亮点
- 多模态输入:支持文本、图片、视频、音频、文档及公开网页
- 视频生成模式:文生视频、首帧/尾帧控制、文件/网页生成
- 输出规格:480p / 720p / 1080p,时长 2–30 秒
- 画面比例:支持 16:9、9:16、1:1、4:3、3:4 及自适应
- 参考素材:最多 10 张图片、5 段视频、5 段音频
- 同步音频:支持语音、音效及背景音乐生成
🎯 适用场景
营销视频 · 社交媒体内容 · 产品展示 · 文档/网页内容可视化 · 多媒体创作
📚 [查看 Wan 3.0 API 文档 →](https://aiboxapi.com/en/api-reference/videos/wan3.0-video/generation)
GPT Image 2.5 Ext
🚀 新品上线
gpt-image-2.5-ext现已登陆 AiBox,支持文生图与图生图,提供 Flare、Sunburst 双版本。核心亮点
- 输出分辨率:1K / 2K / 4K
- 批量生成:每次 1–4 张图片
- 参考图片:最多 16 张,无额外输入图费用
- 画面比例:支持自动及 10 种预设比例
- 灵活计费:按版本、分辨率与实际交付张数结算
适用场景
营销素材 · 社交媒体配图 · 图片改创 · 多尺寸视觉创作
[查看 GPT Image 2.5 Ext API 文档 →](https://aiboxapi.com/en/api-reference/images/gpt-image-2.5-ext/generation)
gpt image 2.5
• We are excited to announce the launch of GPT Image 2.5 on AiBox, featuring Flare and Sunburst for high-quality image generation and precise editing, with flexible quality settings and multiple reference images.
## New Models
GPT Image 2.5 Flare
- Model ID: gpt-image-2.5-flare
- Focus: Fast, high-quality image generation for everyday creative workflows
- Use Cases: Social media content, product images, rapid prototyping, and batch generation
GPT Image 2.5 Sunburst
- Model ID: gpt-image-2.5-sunburst
- Focus: Precise image editing and detailed visual refinement
- Use Cases: Advertising creatives, polished product imagery, and edits requiring fine control
## Key Capabilities
- Text-to-Image: Generate images directly from text prompts - Image-to-Image: Edit and transform images using prompts and reference inputs - Multiple References: Combine up to 16 reference images in one request - Resolution Presets: Choose from 1K, 2K, and 4K presets; resolutions above 2560×1440 are experimental - Custom Dimensions: Specify exact pixel dimensions within supported size limits - Quality Settings: Low, Medium, High, XHigh, Max, and Auto - Multiple Aspect Ratios: 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 2:1, 1:2, 21:9, 9:21, 3:1, and 1:3, plus Auto sizing - Transparent Backgrounds: Generate transparent images in PNG or WebP - Multiple Outputs: Generate 1–4 images per request - Output Formats: PNG, JPEG, and WebP, with adjustable compression for JPEG and WebP
## Documentation
- [GPT Image 2.5 API Documentation](https://aiboxapi.com/en/api-reference/images/gpt-image-2.5/generation)
gemini-omni-1.1-flash
🚀 新品上线
Google 官方视频生成模型 gemini-omni-1.1-flash 现已正式登陆 AiBox。
✨ 核心亮点
生成模式:文生视频、图生视频、首尾帧插值、视频编辑
输出规格:360p / 720p / 1080p / 4K,含音频
画面比例:16:9、9:16
视频时长:约 3–10 秒(由模型决定)
🎯 适用场景
营销素材、社交媒体短视频、创意原型
📚 [查看 Omni-Flash-Ext API 文档](https://aiboxapi.com/en/api-reference/videos/gemini-omni-1.1-flash/generation)
[Notice] Price Adjustment for Seedream-5-0-lite
Due to an upstream pricing adjustment, we will update the price of Seedream-5-0-lite accordingly.
Effective Date: September 3, 2026, at 12:00 PM (UTC+8) / September 3, 2026, at 04:00 AM (UTC+0)
Tasks submitted before this time will still be billed at the original rate.
━━━━━━━━━━━━━━━━━━━━
■ seedream-5-0-lite
Single Image Generation
$0.02275 → $0.028 per image
0.224 Credits → 0.28 Credits
━━━━━━━━━━━━━━━━━━━━
Prices for all other models remain unchanged. Please contact us if you have any questions.
[Notice] Price Adjustment for DeepSeek-V4-Flash
Due to changes in our upstream provider’s billing policy, DeepSeek-V4-Flash will move from a single flat-rate pricing structure to separate Peak and Off-Peak pricing. We have updated the corresponding prices accordingly.
Effective Date: September 3, 2026, at 12:00 PM (UTC+8) / September 3, 2026, at 04:00 AM (UTC+0)
Tasks submitted before this time will still be billed at the original rates.
━━━━━━━━━━━━━━━━━━━━
■ deepseek-v4-flash
Peak
Applicable Period:
UTC+8: Monday–Sunday, 08:00–22:00 UTC+0: Monday–Sunday, 00:00–14:00
Input
$0.3428568 per 1M tokens (3.428568 Credits)
Cached Input
$0.0685712 per 1M tokens (0.685712 Credits)
Output
$1.0285712 per 1M tokens (10.285712 Credits)
Off-Peak
Applicable Period:
UTC+8: Monday–Sunday, 22:00–08:00 the following day UTC+0: Monday–Sunday, 14:00–00:00 the following day
Input
$0.01714284 per 1M tokens (0.1714284 Credits)
Cached Input
$0.00342856 per 1M tokens (0.0342856 Credits)
Output
$0.05142856 per 1M tokens (0.5142856 Credits)
━━━━━━━━━━━━━━━━━━━━
Note on Peak / Off-Peak Pricing:
After the effective time, DeepSeek-V4-Flash will no longer use a single flat rate. Requests will be billed according to the applicable Peak or Off-Peak period.
Prices for all other models remain unchanged. Please contact us if you have any questions.
[Notice] Price Adjustment for Seedream Models
The upstream official vendor for the Seedream image model series recently updated its pricing. Following a recalculation based on the new official rates, we need to adjust the prices for the models listed below accordingly.
Effective Date: August 21, 2026, at 12:00 PM (UTC+8)
Tasks submitted before this time will still be billed at the original rates.
━━━━━━━━━━━━━━━━━━━━
■ seedream-5-0-pro (Tiered by output image pixels)
Single Image Generation
1.5K and below (≤ 2.61M pixels): $0.02928 → $0.02925 (0.2925 Credits)
Above 1.5K (> 2.61M pixels): $0.05856 → $0.0585 (0.585 Credits)
Layer Decomposition (Half price per tier)
1K: $0.01464 → $0.014625 (0.14625 Credits)
2K: $0.02928 → $0.02925 (0.2925 Credits)
Reference Image Input
1st image: Still free
2nd image onward: $0.00195 per image (0.0195 Credits)
■ seedream-5-0-lite
$0.0228 → $0.02275 (0.2275 Credits)
■ seedream-4-5
$0.0228 → $0.026 (0.26 Credits)
■ seedream-4-0
$0.0182 → $0.0195 (0.195 Credits)
━━━━━━━━━━━━━━━━━━━━
Note on Pixel Tiers:
Common dimensions examples:
1536×1536 (~2.36M pixels) falls into the 1.5K and below tier.
2048×2048 (~4.19M pixels) falls into the Above 1.5K tier.
Prices for all other models remain unchanged. Please contact us if you have any questions.
grok-image-2-ext
We are excited to announce the launch of Grok Imagine 2.0 Ext, xAI’s latest high-quality image generation model, now available through AiBox.
## New Model
Grok Imagine 2.0 Ext
- Model ID: grok-imagine-2.0-ext
- Features: High-quality text-to-image generation
- Highlights: Generate up to 12 images in a single request with flexible aspect-ratio support
- Quality: Fixed high-quality generation mode
- Output: URL-based image results valid for 72 hours
## Key Capabilities
- Text-to-Image: Generate detailed images directly from natural-language prompts
- Multiple Image Generation: Generate between 1 and 12 images per request
- Multiple Aspect Ratios: Support for 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, and 16:9
- High-Quality Output: Optimized for detailed, production-ready image generation
- Asynchronous Tasks: Submit generation tasks and retrieve results through task-status polling
- URL-Based Results: Receive downloadable image URLs with a 72-hour validity period
## Documentation
- Grok Imagine 2.0 Ext API Documentation (https://aiboxapi.com/en/api-reference/images/grok-imagine-2.0-ext/generation)
wan3.0
We are excited to announce the launch of Wan 3.0, Alibaba Cloud's latest all-in-one video generation model with multimodal reference support and integrated audio generation capabilities.
## New Model
Wan 3.0
- Model ID: wan3.0-video
- Features: General video generation, frame-to-video generation, and file/webpage-to-video generation
- Highlights: One unified model supporting text prompts, images, videos, audio, documents, and public webpages
- Resolution: 480p / 720p / 1080p
- Duration: 2–30 seconds
## Key Capabilities
- General Generation: Create videos from text prompts alone or combine prompts with image, video, and audio references - Frame-to-Video: Animate a required first frame with an optional last frame for controlled transitions - File and Webpage Generation: Generate videos directly from documents, presentations, PDFs, text files, or public webpages
- Audio Generation: Generate synchronized output audio, including speech, sound effects, and background music
- Multiple Aspect Ratios: 16:9, 9:16, 1:1, 4:3, 3:4, and Adaptive
- Multimodal References: Support for up to 10 images, 5 video clips, and 5 audio clips
## Documentation
- Wan 3.0 API Documentation (https://aiboxapi.com/en/api-reference/videos/wan3.0-video/generation)
doubao-seedance-2-5
We are excited to announce the launch of Doubao Seedance 2.5, an advanced multimodal video generation model supporting longer videos, synchronized audio, and rich reference inputs.
## New Model
Doubao Seedance 2.5
- Model ID: doubao-seedance-2.5
- Features: Text-to-Video, Image-to-Video, video editing, video extension, and multimodal generation
- Highlights: Supports images, videos, and audio as reference inputs with optional synchronized audio generation
- Resolution: 480p / 720p
- Duration: 4–30 seconds or automatic duration
## Key Capabilities
- Text-to-Video: Generate videos directly from text prompts
- Image-to-Video: Animate images using first-frame, last-frame, or reference-image roles
- Video References: Use reference videos for editing, extension, motion, and style guidance
- Audio References: Support audio-guided generation, including pure audio reference workflows
- Audio Generation: Optionally generate synchronized audio alongside the video
- Multimodal Inputs: Combine image, video, and audio references in one request
- Multiple Aspect Ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and Adaptive
- Reference Limits: Up to 30 images, 10 videos, and 10 audio files
- Output Formats: MP4 and MOV
## Documentation
- Doubao Seedance 2.5 API Documentation (https://aiboxapi.com/en/api-reference/videos/doubao-seedance-2-5/generation)
QWEN-IMAGE-3-0
> 🚀 New Model Live > > Image generation models
qwen-image-3.0andqwen-image-3.0-proare now available on AiBox.✨ Key Features
| Capability | Details | | --- | --- | | Generation modes | Text-to-image and image-to-image editing (up to 3 reference images) | | Output resolution | 1K / 2K | | Aspect ratios | 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3 (custom pixel sizes supported) | | Images per request | 1–6 | | Text & layout | Strong bilingual text rendering; Pro is better for dense layouts such as menus, posters, and storyboards | | Prompt extend | Optional
prompt_extend(direct/agent) |🎯 Best For
- Marketing posters and campaign creatives
- E-commerce menus, product sheets, and text-heavy visuals
- Social media assets and rapid creative prototyping
📚 [View Qwen Image 3.0 API docs](https://aiboxapi.com/en/api-reference/images/qwen-image-3.0/generation)
FLUX-3-VIDEO
> 🚀 New Model Launch > > The
flux-3-videovideo generation model is now available on AiBox.✨ Key Highlights
| Capability | Description | | --- | --- | | Generation Modes | Text-to-video, image-to-video, and video continuation | | Draft Mode | Generate a low-cost draft, then render the final video once satisfied | | Output Quality | HD / FHD | | Video Duration | 5–20 seconds | | Keyframes | Supports 1–10 ordered keyframes | | Aspect Ratios | Auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, and 9:16 | | Audio Generation | Synchronized audio is enabled by default and can be disabled |
🎯 Use Cases
- Generate videos from text or images
- Control video content with start/end frames or multiple keyframes
- Continue an existing video
- Preview ideas with low-cost drafts before rendering the final video
📚 [View the FLUX 3 Video API Documentation](https://aiboxapi.com/en/api-reference/videos/flux-3-video/generation)
Minimax-h3
We are excited to announce the launch of MiniMax H3, MiniMax’s latest multimodal video generation model with native 2K output and synchronized audio.
New Model
MiniMax H3
• Model ID: MiniMax-H3 • Features: Text-to-Video and Image-to-Video (first/last frame), plus multimodal reference generation (images, video, and audio) • Highlights: Unified omnimodal model for T2V / I2V / reference-to-video with native audio on every result • Resolution: 2K • Duration: 4–15 seconds
Key Capabilities
• Text-to-Video: Generate videos directly from text prompts • Image-to-Video: Animate with first-frame and optional last-frame control • Omni Reference: Guide generation with reference images (≤9), videos (≤3), and audio (≤3; must pair with image or video) • Native Audio: All outputs include synchronized stereo audio • Multiple Aspect Ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, and Adaptive (I2V follows input image) • Watermark: Optional AIGC watermark
Documentation
• MiniMax H3 API Documentation (https://aiboxapi.com/en/api-reference/videos/minimax-h3/generation)
Try it on AiBox
• Model page: https://aiboxapi.com/model/minimax-h3
FLUX
We are excited to announce the launch of FLUX.1 Kontext and FLUX.2, Black Forest Labs’ advanced image generation and editing model families, now available through AiBox’s unified image API.
## New Models
### FLUX.1 Kontext
FLUX.1 Kontext Pro
- Model ID:
flux-kontext-pro - Features: Context-aware image editing and text-to-image generation
- Highlights: Faster generation with predictable per-image pricing
- Reference Images: Up to 4 images
FLUX.1 Kontext Max
- Model ID:
flux-kontext-max - Features: Context-aware image editing and text-to-image generation
- Highlights: Higher-quality output for demanding creative workflows
- Reference Images: Up to 4 images
### FLUX.2
FLUX.2 Pro
- Model ID:
flux-2-pro - Features: Image generation and multi-reference image editing
- Highlights: Balanced speed, quality, and cost
- Reference Images: Up to 8 images
FLUX.2 Max
- Model ID:
flux-2-max - Features: High-quality image generation and editing
- Highlights: Maximum output quality for professional workflows
- Reference Images: Up to 8 images
FLUX.2 Flex
- Model ID:
flux-2-flex - Features: Controllable image generation and editing
- Highlights: Adjustable steps and guidance for fine-grained creative control
- Reference Images: Up to 8 images
## Key Capabilities
- Text-to-Image: Generate new images directly from text descriptions
- Image Editing: Modify subjects, objects, backgrounds, colors, compositions, and visual styles
- Multi-Reference Generation: Use multiple reference images to guide identity, composition, and style
- Context-Aware Editing: Preserve visual context while applying natural-language editing instructions
- Flexible Output Sizes: Generate images at 512px, 1K, or 2K resolution with supported aspect ratios
- Prompt Enhancement: Automatically expand prompts with optional
prompt_upsampling - Repeatable Results: Reuse a fixed
seedwith the same inputs to help reproduce an image - Multiple Output Formats: Export generated images as PNG, JPEG, or WebP
- Unified Asynchronous API: Access every FLUX model through the same task submission and polling workflow
## Documentation
- [FLUX.1 Kontext API Documentation](https://aiboxapi.com/en/api-reference/images/flux-kontext/generation)
- [FLUX.2 API Documentation](https://aiboxapi.com/en/api-reference/images/flux-2/generation)
- Model ID:
GPT Image 2: Transparent Token Pricing Now on the Model Page
We have updated the GPT Image 2 model page with transparent token-based pricing details.
What's New
Token Pricing Table
The pricing calculator on the [GPT Image 2 model page](https://aiboxapi.com/model/gpt-image-2) now displays a token price breakdown for
gpt-image-2-official, shown in Credits per 1M tokens:| Type | Price | | --- | --- | | Text input | 50 Credits / 1M tokens | | Cached text input | 12.5 Credits / 1M tokens | | Image input | 80 Credits / 1M tokens | | Cached image input | 20 Credits / 1M tokens | | Image output | 300 Credits / 1M tokens |
Improvements
- Token Price Breakdown: See exactly how each modality (text/image, input/cached input/output) is billed before you generate
- Credits Display: All token prices are converted to Credits, consistent with the rest of the platform
- Live Estimate: The calculator still shows the estimated per-image price with the current token consumption for your selected size, resolution, and quality
Suno
We are excited to announce the launch of the Suno Music API on AiBox, a complete AI music generation and production toolchain with 31 endpoints covering creation, editing, and export.
New Model
Suno
- Model ID:
suno - Features: Text-to-Music generation with a full suite of derivative and post-processing endpoints
- Highlights: Unified API covering generation, extension, covers, stem separation, voice personas, audio editing, and analysis
- Versions: v3.5 / v4 / v4.5 / v4.5+ / v4.5-all / v5 / v5.5
- Output: Two candidate tracks per generation, with streaming audio, cover art, and lyrics
Key Capabilities
- Music Generation: Inspiration mode (describe the song you want) and Custom mode (full control over lyrics, title, style tags, negative tags, vocal gender, and style / weirdness / audio weights)
- Lyrics Generation: Standalone lyrics endpoint with selectable lyrics models (
classic/remi) - Audio Upload: Bring your own audio as the source for extension, covers, and vocal / instrumental additions
- Derivative Works: Extend, Cover, Remaster, Add Vocals, Add Instrumental, Add Stem, Mashup, and Sample-to-Song
- Stem Separation: 4-track separation, full 12-instrument separation, and isolated vocal (Vox) extraction
- Voice Personas: Create reusable voice personas from generated tracks and apply them to new generations
- Audio Editing: Replace Section, Remove Section, Crop, Fade In / Fade Out, Adjust Speed (0.25x–4x with optional pitch preservation), and Full Song synthesis from extended clips
- Analysis & Export: Word-level aligned lyrics timeline, BPM analysis, MIDI generation, Music Video (MP4) rendering, and WAV export
Documentation
- [Suno API Documentation](https://aiboxapi.com/en/api-reference/audios/suno/overview)
- Model ID:
FlowMusic
we are excited to announce that FlowMusic — a full-stack AI music generation suite — is now available on AiBox.
Turn a single prompt or lyric into studio-ready songs, stems, and music videos. Powered by an upgraded Producer engine (default model Lyria 3 Pro), FlowMusic bundles nine music-creation capabilities — generation, extension, replacement, cover, stem separation, import, download, and video rendering — into one unified async task-based API, so you can build an entire song lifecycle end to end.
- Model ID:
flowmusic - Capabilities: Music Generation, Lyrics Generation, Extend, Replace, Cover, Stem Separation, Audio Import, Format Export, Music Video Rendering
- Highlights: 9 endpoints in one model, lossless WAV + streaming M4A, auto-generated cover art, karaoke timing markers, async task API
- Output: M4A (streaming) + WAV (lossless) + optional MP4 music video
- Controls: BPM, length up to 240s, seed for reproducibility
🚀 Key Capabilities
- Text/Lyrics-to-Music: Generate a full song from a sound prompt and/or lyrics, with control over BPM, length (up to 240s), and seed — each request returns one track
- Lyrics Generation: Turn any idea into structured lyrics (≤ 3000 chars), then feed them straight back into music generation
- Music Extend: Continue an existing clip from any timestamp — up to 327 seconds of new audio — guided by a natural-language instruction
- Section Replace: Regenerate a specific time range within a song (e.g. swap a chorus to piano) without touching the rest
- Cover / Restyle: Re-arrange a whole track into a new style with adjustable edit strength (0–1)
- Stem Separation: Split vocals and accompaniment into a downloadable multi-track ZIP
- Audio Import: Bring external audio in via
audio_urlto obtain aclip_idfor downstream editing - Format Export: Download any clip as
wavormp3 - Music Video Rendering: Render a clip into MP4 with
simple/modern/playerpresets - Karaoke Timing: Lyrics timing markers included for word-level highlighting
- Usage-based Billing: Charged on submission with full auto-refund on task failure ($0.06 generate/extend/replace/cover/stems · $0.02 lyrics/download/video · $0.01 import)
🎯 Best For
- Producing complete, lyric-driven songs from a single text idea
- Iterating on tracks — extend, replace a section, or restyle without starting over
- Generating royalty-style background music for video, ads, and games
- Building karaoke experiences with word-level lyric timing
- Extracting stems for remixing and post-production
- Turning existing audio into new covers and arrangements
## 📚 Documentation - [FlowMusic](https://aiboxapi.com/en/api-reference/audios/flow-music/music)
- Model ID:
seedream-5-0-pro
We are excited to announce the launch of Seedream 5.0 Pro, ByteDance's latest quality-first text-to-image model with best-in-class text rendering and unified generation and editing.
New Model
Seedream 5.0 Pro
- Model ID:
doubao-seedream-5-0-pro - Features: Text-to-Image and Image-to-Image generation with unified editing in a single API call
- Highlights: Cinematic, quality-first image generation with industry-leading text rendering
- Resolution: 1K / 2K (default 2K)
- Output: One image per request (PNG / JPEG)
Key Capabilities
- Text-to-Image: Generate cinematic, richly detailed images directly from text descriptions
- Image-to-Image: Edit and refine existing images — remove objects, replace backgrounds, or restyle with simple prompts
- Perfect Text Rendering: Produce accurate, readable text in images for posters, banners, and marketing visuals
- Multi-Reference Fusion: Blend subjects, styles, and outfits from multiple reference images in one request
- Multiple Aspect Ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9, and Auto
- Reference Images: Support for up to 10 reference images for style and character consistency
- Watermark: Optional watermark on generated images
Notes
- Quality-first model that prioritizes fidelity and detail over raw speed (1K ~90s, 2K ~160s)
- Asynchronous generation: submit to
/v1/images/generations, then poll/v1/tasks/{task_id}until the task completes
Documentation
- [Seedream 5.0 Pro API Documentation](https://aiboxapi.com/en/api-reference/images/seedream-5-0-pro/generation)
- Model ID:
gemini-3.1-flash-lite-image-ext
We've added `gemini-3.1-flash-lite-image-ext` — a fast, low-cost image generation model now available on the Nano Banana page. Select it directly from the model dropdown to get started.
Capabilities
- Text-to-image & image-to-image — generate from a prompt, or guide generation with reference images.
- Up to 14 reference images per request.
- Aspect ratios:
1:1,2:3,3:2,3:4,4:3,4:5,5:4,9:16,16:9,21:9. - Fast & cost-efficient — optimized for low-latency, high-volume generation.
Try it now: [Nano Banana Lite Playground](/model/nano-banana-3-api)
API Docs: https://aiboxapi.com/en/api-reference/images/gemini-3.1-flash/generation-lite
gemini-3.1-flash-lite-image
We're excited to announce Gemini 3.1 Flash Lite Image (Nano Banana Lite) — the fastest and most affordable image model in Google's Gemini 3.1 series. Built for high-volume, real-time, and budget-sensitive workflows, it delivers high-quality images with low latency and low cost.
Model ID:
gemini-3.1-flash-lite-imageHighlights
- Fast & low-cost — optimized for speed and scale, billed by input/output tokens
- Text-to-Image & Image-to-Image — one model for generation and reference-guided editing
- Multi-image reference — up to 14 reference images per request
Key Capabilities
- Text-to-Image — generate images directly from text prompts
- Image-to-Image — edit or restyle from reference images with a natural-language instruction
- Multiple Aspect Ratios — 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
- Reference Images — supply 1–14 images (e.g. objects + characters) to guide generation
Get Started
See the [Gemini 3.1 Flash Lite Image API Documentation](https://aiboxapi.com/en/api-reference/images/gemini-3.1-flash/generation-lite) for request parameters and examples.
gemini-omni-flash-preview
we are excited to announce that Google's Gemini Omni Flash omni-multimodal video generation model is now available on AiBox.
Generate videos with synced audio from text prompts, reference images, or reference videos — and even mix text + image + video in a single request. Powered by Google's official Gemini Omni Flash, it supports conversational, multi-turn editing so you can iterate on a clip without re-uploading anything, all through one unified async task-based API.
- Model ID:
gemini-omni-flash-preview - Generation Modes: Text-to-Video, Image-to-Video, Video-to-Video
- Highlights: Omni multimodal input (text + image + video mixed), conversational multi-turn editing, audio output included, async task API
- Resolution: 720P
- Sizes: 16:9, 9:16
- Duration: 1 – 24 seconds (content-driven, no duration parameter)
🚀 Key Capabilities
- Text-to-Video: Generate dynamic 720p clips with synced audio directly from natural language prompts, with control over subject, scene, motion, and atmosphere
- Image-to-Video: Provide up to 16 reference images through
image_urlsto guide visual style, subject appearance, or scene composition — multi-subject prompts supported - Video-to-Video (Editing): Supply a reference video via
video_urlsto transform environment, add effects, or restyle footage using text instructions - Omni Multimodal Input: Mix text + image + video in a single request (e.g. one character image + one reference clip + a text instruction)
- Conversational Multi-turn Editing: Use
extend_from_task_idto iterate on your previous result — the model keeps the video context, changes only what you ask, and requires no re-upload - Synced Audio Output: Videos are generated with audio included by default
- Natural-language Timing Control: Since there is no
durationparameter, guide pacing/length directly in the prompt (e.g. "after 3 seconds ...", "[0-3s] ...") - Aspect Ratio Control: Choose
16:9(landscape) or9:16(portrait) to control true output orientation - Async Task API: Submit a job, receive a
task_id, and poll for status and results - Token-based Billing: Pay for real usage on AiBox — settled by actual upstream token consumption, with no charge on task failure
🎯 Best For
- Text-to-video clips with synced audio for social and short-form content
- Iterative, conversation-style video editing without re-uploading source clips
- Turning sketches or reference images into motion drafts
- Restyling and effect experiments on short reference footage
- Multi-subject scene animation from mixed image + text input
- Rapid creative exploration where audio-included previews matter
## 📚 Documentation - [Gemini Omni Flash](https://aiboxapi.com/en/api-reference/videos/gemini-omni-flash-preview/generation)
- Model ID: