# EvoLink.AI: English API Manual

## API Manual

### Image Series

#### Nanobanana

- [Nanobanana 2 Lite Image Generation](https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-2-lite-image-generate.md): - Nano Banana 2 Lite (gemini-3.1-flash-lite-image) model supports text-to-image, image-to-image, image editing and other generation modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours…
- [Nanobanana 2 Lite Beta Image Generation](https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-2-lite-beta-image-generate.md): - Nano Banana 2 Lite Beta (nano-banana-2-lite-beta) model supports text-to-image, image-to-image, image editing and other generation modes, with fixed 1K output for fast, cost-sensitive image generation - It is generally consistent with Nano Banana 2 Lite, but does not support the `model_params.thin…
- [Nanobanana 2 Image Generation](https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-2-image-generate.md): - Nano Banana 2 (gemini-3.1-flash-image-preview) model supports text-to-image, image-to-image, image editing and other generation modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours,…
- [Nanobanana-2 Image Generation Beta](https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-2-beta-image-generate.md): - Nano Banana 2 Beta (nano-banana-2-beta) model supports text-to-image, image-to-image, image editing and other generation modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please…
- [Nanobanana Pro Image Generation](https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-pro-image-generate.md): - Nano Banana Pro (gemini-3-pro-image-preview) model supports text-to-image, image-to-image, image editing and other generation modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, pl…
- [Nanobanana Pro Image Generation Beta](https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-pro-beta-image-generate.md): - Nano Banana Pro Beta (nano-banana-pro-beta) model supports text-to-image, image-to-image, image editing and other generation modes, cost-effective - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid f…
- [Nanobanana Image Generation Beta](https://evolink.ai/docs/en/api-manual/image-series/nanobanana/nanobanana-image-generate.md): - Nano Banana (nano-banana-beta) model supports text-to-image, image-to-image, image editing and other generation modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please save them…

#### Grok

- [Grok Imagine Image 2.0 Image Generation](https://evolink.ai/docs/en/api-manual/image-series/grok/grok-imagine-image-2.0-image-generate.md): - Grok Imagine Image 2.0 (grok-imagine-image-2.0) is xAI's image generation and editing model — text-to-image and image editing share the same model name - Omit `image_urls` for text-to-image; pass `1~3` reference images and it automatically switches to image editing, no model change needed - Asynch…

#### Midjourney

##### Midjourney V8.1

- [Midjourney V8.1 Prompt Parameter Guide](https://evolink.ai/docs/en/api-manual/image-series/midjourney/midjourney-v8-1-prompt-guide.md): All available parameters for the Midjourney V8.1 model in prompts, including value ranges, defaults, dependencies, and conflicts
- [Midjourney V8.1 Image Generation](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-image-generate.md): - Midjourney V8.1 model supports generating high-quality images via natural language prompts. Fast mode returns 4 images per generation; Draft mode returns 24 lightweight 0.5K sketch images in a single run - Supports text-to-image and image-to-image (reference image URLs in prompt) - V8.1 highlights…
- [Midjourney V8.1 Variation](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-variation.md): - Based on completed mj-v8.1 series tasks, generate style variants with differences for the specified image - The prompt has no effect on variation output (it only produces style variants of the source image); to guide the changes with a prompt, use mj-v8.1-remix instead - Async processing mode, use…
- [Midjourney V8.1 Remix](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-remix.md): - Re-create previously generated images with new prompts - Change content or style while preserving the original image structure - Difference from variation: remix requires a prompt to reinterpret the original - Async processing mode, use the returned task ID to [query status](/en/api-manual/task-ma…
- [Midjourney V8.1 Retexture](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-retexture.md): - Change image texture and style while preserving original structure - Does not depend on a source task, directly pass in image URL - Async processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail)
- [Midjourney V8.1 Upload Paint](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-upload-paint.md): - Upload images for advanced canvas editing, supporting mask area specification and position adjustment - Similar to mj-v8.1-edit, but does not depend on existing tasks, directly pass in images - Async processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-tas…
- [Midjourney V8.1 Canvas Edit](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-edit.md): - Reposition the image of an existing task on the canvas and fill blank areas with AI - Suitable for adjusting composition, expanding scenes (outpaint), repainting, etc. - Async processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail)
- [Midjourney V8.1 Remove Background](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v8-1-remove-bg.md): - Automatically remove image background and generate transparent images - The simplest model, only requires one input image - Does not depend on a source task, directly pass in image URL - Does not support prompt, speed or other parameters - Async processing mode, use the returned task ID to [query…

##### Midjourney V7

- [Midjourney V7 Prompt Parameter Guide](https://evolink.ai/docs/en/api-manual/image-series/midjourney/midjourney-v7-prompt-guide.md): All available parameters for the Midjourney V7 model in prompts, including value ranges, defaults, dependencies, and conflicts
- [Midjourney V7 Image Generation](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-image-generate.md): - Midjourney V7 model supports generating high-quality images via natural language prompts, 4 images per generation - Supports text-to-image and image-to-image (reference image URLs in prompt) - Supports all V7 native parameter syntax (e.g. --ar, --s, --c), see [Prompt Parameter Guide](/en/api-manua…
- [Midjourney V7 Variation](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-variation.md): - Based on completed mj-v7 series tasks, generate style variants with differences for the specified image - Supports optional prompt; if provided, content is modified along with the variation - Async processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-…
- [Midjourney V7 Upscale](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-upscale.md): - Upscale generated images to higher resolution - Supports two modes: standard and creative - Already upscaled images cannot be upscaled again (will return 403 error) - Async processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail)
- [Midjourney V7 Remix](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-remix.md): - Re-create previously generated images with new prompts - Change content or style while preserving the original image structure - Difference from variation: remix requires a prompt to reinterpret the original - Async processing mode, use the returned task ID to [query status](/en/api-manual/task-ma…
- [Midjourney V7 Enhance](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-enhance.md)
- [Midjourney V7 Pan](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-pan.md)
- [Midjourney V7 Outpaint](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-outpaint.md)
- [Midjourney V7 Inpaint](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-inpaint.md)
- [Midjourney V7 Canvas Edit](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-edit.md): - Reposition generated images on the canvas and fill blank areas with AI - Suitable for adjusting composition, expanding scenes, etc. - Async processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail)
- [Midjourney V7 Remove Background](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-remove-bg.md): - Automatically remove image background and generate transparent images - The simplest model, only requires one input image - Does not depend on a source task, directly pass in image URL - Does not support prompt, speed or other parameters - Async processing mode, use the returned task ID to [query…
- [Midjourney V7 Retexture](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-retexture.md): - Change image texture and style while preserving original structure - Does not depend on a source task, directly pass in image URL - Retextured tasks only support upscale as follow-up - Async processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail)
- [Midjourney V7 Upload Paint](https://evolink.ai/docs/en/api-manual/image-series/midjourney/mj-v7-upload-paint.md): - Upload images for advanced canvas editing, supporting mask area specification and position adjustment - Similar to mj-v7-edit, but does not depend on existing tasks, directly pass in images - Async processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-…

#### GPT Image

- [GPT Image 2 Image Generation](https://evolink.ai/docs/en/api-manual/image-series/gpt-image-2/gpt-image-2-image-generation.md): - GPT Image 2 (gpt-image-2) model supports text-to-image, image-to-image, image editing and other generation modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please save them prom…
- [GPT Image 2 Image Generation Beta](https://evolink.ai/docs/en/api-manual/image-series/gpt-image-2/gpt-image-2-beta-image-generation.md): - GPT Image 2 (gpt-image-2-beta) model supports text-to-image, image-to-image, and image editing modes - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please save them promptly
- [GPT Image 1.5 Image Generation](https://evolink.ai/docs/en/api-manual/image-series/gpt-image-1.5/gpt-image-1.5-image-generation.md): - GPT Image 1.5 (gpt-image-1.5) model supports text-to-image, image-to-image, and image editing modes - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please save them promptly

#### Seedream

- [Seedream 5.0 Pro Image Generation](https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-5.0-pro-image-generate.md): - Seedream 5.0 Pro (doubao-seedream-5.0-pro) model supports text-to-image, image-to-image, image editing and other generation modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, plea…
- [Seedream 5.0 Pro Layer Decomposition](https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-5.0-pro-layerize-image-generate.md): - Seedream 5.0 Pro Layer Decomposition (doubao-seedream-5.0-pro-layerize) splits one image into a base image and several independent layers; every layer is a PNG with an alpha channel, while the base image format follows `output_format` - Exactly **one** input image is required; `prompt` is optional…
- [Seedream 5.0 Lite Image Generation](https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-5.0-lite-image-generate.md): - Seedream 5.0 Lite (doubao-seedream-5.0-lite) model supports text-to-image, image-to-image, image editing and other generation modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, pl…
- [Seedream 4.5 Image Generation](https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-4.5-image-generate.md): - Seedream 4.5 (doubao-seedream-4.5) model supports text-to-image, image-to-image, image editing and other generation modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please save…
- [Seedream-4.0 Image Generation](https://evolink.ai/docs/en/api-manual/image-series/seedream/seedream-4.0-image-generate.md): - Seedream 4.0 (doubao-seedream-4.0) model supports text-to-image, image-to-image, image editing and other generation modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please save…

#### Z Image Turbo

- [Z Image Turbo Image Generation](https://evolink.ai/docs/en/api-manual/image-series/z-image-turbo/z-image-turbo-image-generate.md): - Z Image Turbo is an ultra-fast text-to-image generation model with exceptional quality - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please save them promptly

#### Qwen-Image

- [Qwen Image 3.0](https://evolink.ai/docs/en/api-manual/image-series/qwen/qwen-image-3.0.md): - Qwen (qwen-image-3.0) is the **standard edition** of Qwen image generation and editing 3.0. It supports the same two modes — text-to-image (T2I, no reference image) and image editing (I2I, with 1-3 reference images) — balancing quality and speed - Request parameters, size semantics and response st…
- [Qwen Image 3.0 Pro](https://evolink.ai/docs/en/api-manual/image-series/qwen/qwen-image-3.0-pro.md): - The Qwen (qwen-image-3.0-pro) model supports both text-to-image (T2I, no reference image) and image editing (I2I, with 1-3 reference images) modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid f…
- [Qwen Image Edit Plus](https://evolink.ai/docs/en/api-manual/image-series/qwen/qwen-image-edit-plus.md): - Qwen (qwen-image-edit-plus) model supports image editing, image-to-image and other modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please save them promptly
- [Qwen Image Edit](https://evolink.ai/docs/en/api-manual/image-series/qwen/qwen-image-edit.md): - Qwen (qwen-image-edit) model supports image editing, image-to-image and other modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please save them promptly

#### Wan-Image

- [Wan2.5 Text to Image](https://evolink.ai/docs/en/api-manual/image-series/wan2.5/wan2.5-text-to-image.md): - WAN2.5 (wan2.5-text-to-image) model supports text-to-image generation mode - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please save them promptly
- [Wan2.5 Image to Image](https://evolink.ai/docs/en/api-manual/image-series/wan2.5/wan2.5-image-to-image.md): - WAN2.5 (wan2.5-image-to-image) model supports image-to-image, image editing and other generation modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image links are valid for 24 hours, please save them promptly

#### Krea

##### Krea 2 Turbo

- [Krea 2 Turbo Image Generation](https://evolink.ai/docs/en/api-manual/image-series/krea/krea-2-turbo-image-generate.md): - Krea 2 Turbo is an ultra-fast text-to-image generation model that produces high-fidelity, cinematic visuals - Text-to-image only; reference images are not supported - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated image…

### Video Series

#### Seedance 2.5

- [Seedance 2.5 Complete Parameter Guide](https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-overview.md): Unified API for all Seedance 2.5 models, select a specific model via the `model` parameter
- [Seedance 2.5 Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-text-to-video.md): - Generate videos from text prompts, supports web search for enhanced timeliness - **Now supports AIGC realistic human materials** - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours…
- [Seedance 2.5 Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-image-to-video.md): - Input 1 image for first-frame video generation, input 2 images for first-last-frame video generation, the model determines automatically - **Now supports AIGC realistic human materials** - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-t…
- [Seedance 2.5 Reference-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-reference-to-video.md): - Input reference images (0–30) + reference videos (0–10) + reference audio (0–10) + a text prompt to generate video; provide at least one image, video, or audio reference - Best suited for generating new footage: images, videos, and audio act as style, subject, camera-movement, and soundtrack refer…
- [Seedance 2.5 Video Edit](https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-video-edit.md): - Video editing on an input video — replace subjects, add/remove objects, restyle or repaint regions - Prompt must state the editing intent (e.g. "Edit the video: remove the background music of @video1") - Input the video to edit (required) + optional reference images (0–30) + reference videos (up t…
- [Seedance 2.5 Video Extend](https://evolink.ai/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-video-extend.md): - Extend an input video forward or backward - Prompt must state the extension intent (e.g. "Extend @video1 backward, the character walks out of the frame") - Input the video to extend (required) + optional reference images (0–30) + reference videos (up to 10 in total) + reference audio (0–10) - **No…

#### Seedance 2.0

- [Seedance 2.0 Complete Parameter Guide](https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-overview.md): Unified API for all Seedance 2.0 models, select a specific model via the `model` parameter
- [Seedance 2.0 Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-text-to-video.md): - Generate videos from text prompts, supports web search for enhanced timeliness - **Now supports AIGC realistic human materials** - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours…
- [Seedance 2.0 Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-image-to-video.md): - Input 1 image for first-frame video generation, input 2 images for first-last-frame video generation, the model determines automatically - **Now supports AIGC realistic human materials** - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-t…
- [Seedance 2.0 Reference-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-reference-to-video.md): - Input reference images (0–9) + reference videos (0–3) + reference audio (0–3) + text prompt to generate video - Supports various creative scenarios including new generation, video editing, and video extension - **Now supports AIGC realistic human materials** - Asynchronous processing mode, use the…
- [Seedance 2.0 Fast Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-fast-text-to-video.md): - Generate videos from text prompts, supports web search for enhanced timeliness - **Now supports AIGC realistic human materials** - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours…
- [Seedance 2.0 Fast Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-fast-image-to-video.md): - Input 1 image for first-frame video generation, input 2 images for first-last-frame video generation, the model determines automatically - **Now supports AIGC realistic human materials** - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-t…
- [Seedance 2.0 Fast Reference-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-fast-reference-to-video.md): - Input reference images (0–9) + reference videos (0–3) + reference audio (0–3) + text prompt to generate video - Supports various creative scenarios including new generation, video editing, and video extension - **Now supports AIGC realistic human materials** - Asynchronous processing mode, use the…
- [Seedance 2.0 Mini Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-mini-text-to-video.md): - Generate videos from text prompts - **Now supports AIGC realistic human materials** - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly
- [Seedance 2.0 Mini Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-mini-image-to-video.md): - Input 1 image for first-frame video generation, input 2 images for first-last-frame video generation, the model determines automatically - **Now supports AIGC realistic human materials** - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-t…
- [Seedance 2.0 Mini Reference-to-Video](https://evolink.ai/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-mini-reference-to-video.md): - Input reference images (0–9) + reference videos (0–3) + reference audio (0–3) + text prompt to generate video - Supports various creative scenarios including new generation, video editing, and video extension - **Now supports AIGC realistic human materials** - Asynchronous processing mode, use the…

#### Minimax

##### Minimax H3

- [Minimax H3 / H3 Max Complete Parameter Guide](https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-overview.md): Unified API for the entire Minimax H3 and H3 Max series. Select the generation mode with the `model` parameter.
- [Minimax H3 Max Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-max-text-to-video.md): - Generate video from a non-empty text prompt - Output duration: `5`–`15` seconds; resolution `480p` or `768p` (default) - Image, video, and audio inputs are not supported - Asynchronous processing; use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generate…
- [Minimax H3 Max Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-max-image-to-video.md): - Provide at least one of `image_start` or `image_end`; first-frame-only, last-frame-only, and first-and-last-frame modes are supported - Output duration: `5`–`15` seconds; resolution `480p` or `768p` (default) - The model automatically adapts the output aspect ratio to the input image; do not send…
- [Minimax H3 Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-text-to-video.md): - Generate video from a non-empty text prompt - Output duration: `4`–`15` seconds; resolution `768p` (default) or `2k` - Image, video, and audio inputs are not supported - Asynchronous processing; use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated…
- [Minimax H3 Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-image-to-video.md): - Provide at least one of `image_start` or `image_end`; first-frame-only, last-frame-only, and first-and-last-frame modes are supported - Output duration: `4`–`15` seconds; resolution `768p` (default) or `2k` - The model automatically adapts the output aspect ratio to the input image; do not send `a…
- [Minimax H3 Reference-to-Video](https://evolink.ai/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-reference-to-video.md): - Supports up to 9 reference images, 3 reference videos, and 3 reference audio clips, and up to 12 reference assets in total - At least one reference asset is required: image, video, or audio - Output duration: `4`–`15` seconds; resolution `768p` (default) or `2k` - Asynchronous processing; use the…

#### Gemini Omni Flash

##### Gemini Omni 1.1 Flash

- [Gemini Omni 1.1 Flash Full Parameter Overview](https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-overview.md): - Full parameter reference for all five Gemini Omni 1.1 Flash video modes - Five modes are available: text-to-video, image-to-video, reference-to-video, video edit, and video extend. - `quality`: Text/Image/Reference support four tiers and default to 720p. Edit/Extend also support auto and default t…
- [Gemini Omni 1.1 Flash Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-text-to-video.md): - Generate a video with native audio from a text prompt - `quality`: Output resolution: 360p, 720p, 1080p, or 4k. Default: 720p. - `duration`: Video duration in seconds. Integer from 3 to 10; default 3. - `aspect_ratio`: Aspect ratio: 16:9, 9:16, or auto; default auto. - The model generates synchron…
- [Gemini Omni 1.1 Flash Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-image-to-video.md): - Generate a video with native audio from one first-frame image or a first-and-last-frame pair - `image_urls`: First/last-frame image URL array. One image is the first frame; with two images, the first is the first frame and the second is the last frame. HTTP/HTTPS image URLs only; png, jpeg, webp.…
- [Gemini Omni 1.1 Flash Reference-to-Video](https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-reference-to-video.md): - Generate a video with native audio from reference images, optional reference videos, and a text prompt - `image_urls`: Reference image URL array. Required; publicly documented maximum: 10 images. HTTP/HTTPS only. - `video_urls`: Optional reference video URLs, up to 3 directly reachable HTTP/HTTPS…
- [Gemini Omni 1.1 Flash Video Edit](https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-video-edit.md): - Edit one input video with optional reference images and a text prompt - `video_urls`: Exactly one directly reachable HTTP/HTTPS MP4, no longer than 10 seconds. - `image_urls`: Optional reference image URLs, up to 10 images. HTTP/HTTPS only. Each image contributes input tokens. - `quality`: Output…
- [Gemini Omni 1.1 Flash Video Extend](https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-video-extend.md): - Extend one input video using optional reference images and a text prompt - `video_urls`: Exactly one directly reachable HTTP/HTTPS MP4, no longer than 30 seconds. - `image_urls`: Optional reference image URLs, up to 10 images. HTTP/HTTPS only. Each image contributes input tokens. - `quality`: Outp…

##### Gemini Omni Flash 1.0

- [Gemini Omni Flash 1.0 Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-text-to-video.md): - The Gemini Omni Flash (gemini-omni-flash-text-to-video) model supports text-to-video mode, producing a video with native audio from a text prompt - **Duration control:** Set an integer duration of `3~10` seconds via `duration`, or pass `auto` to let the model decide - **Aspect ratio:** Choose `16:…
- [Gemini Omni Flash 1.0 Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-image-to-video.md): - The Gemini Omni Flash (gemini-omni-flash-image-to-video) model supports image-to-video mode, producing a video with native audio from an input image and a text prompt - **Image input:** Provided via `image_urls`; currently only 1 image is supported - **Duration control:** Set an integer duration o…
- [Gemini Omni Flash 1.0 Reference-to-Video](https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-reference-to-video.md): - The Gemini Omni Flash (gemini-omni-flash-reference-to-video) model supports reference-to-video mode, producing a video with native audio from 1~6 reference images and a text prompt - **Reference image input:** Provided via `image_urls`, supports 1~6 images, used to constrain the subject, style, or…
- [Gemini Omni Flash 1.0 Video Edit](https://evolink.ai/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-video-edit.md): - The Gemini Omni Flash (gemini-omni-flash-video-edit) model supports video editing mode, producing an edited video from an input video and a text prompt - **Video input:** Provided via `video_urls`; only 1 video is supported, and the input video must be 3-10 seconds long - **Editing instructions:**…

#### Kling

- [Kling Custom Element](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-custom-element.md): - Kling Custom Element (kling-custom-element) creates reusable subject elements (characters/objects) from reference images or videos - After successful creation, the returned `element_id` can be referenced in Kling O3 series and Kling V3 Image-to-Video via the `element_list` parameter, enabling cons…

##### Kling-O3

- [Kling-O3 Text to Video](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o3-text-to-video.md): - Kling-O3 Text to Video (kling-o3-text-to-video) pure text-driven video generation, based on Kling AI kling-v3-omni model - Supports single-shot and multi-shot modes, can generate videos with sound effects - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/tas…
- [Kling-O3 Image to Video](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o3-image-to-video.md): - Kling-O3 Image to Video (kling-o3-image-to-video) generates videos based on input images, powered by the Kling AI kling-v3-omni model - Supports first frame, last frame, reference images, element control, multi-shot, and sound effects - Asynchronous processing mode, use the returned task ID to [qu…
- [Kling-O3 Reference to Video](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o3-reference-to-video.md): - Kling-O3 Reference to Video (kling-o3-reference-to-video) generates new videos based on the style and motion characteristics of a reference video, powered by the Kling AI kling-v3-omni model - The reference video serves as a feature reference (not direct editing), and can be combined with text, re…
- [Kling-O3 Video Edit](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o3-video-edit.md): - Kling-O3 Video Edit (kling-o3-video-edit) edits and modifies the original video, based on the Kling AI kling-v3-omni model - Output video duration and aspect ratio remain consistent with the input video - Supports editing with text instructions, reference images, and elements - Sound generation is…

##### Kling-V3

- [Kling-V3 Text to Video](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v3-text-to-video.md): - Kling-V3 Text to Video (kling-v3-text-to-video) model supports text-to-video generation - Supports single-shot and multi-shot modes, capable of generating videos with sound effects - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-de…
- [Kling-V3 Image to Video](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v3-image-to-video.md): - Kling-V3 Image to Video (kling-v3-image-to-video) model supports image-to-video generation - Supports first frame, last frame, element control, multi-shot, and sound effects - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) -…
- [Kling-V3 Motion Control](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v3-motion-control.md): - Kling-V3 Motion Control (kling-v3-motion-control) model supports generating motion-driven videos using **reference image + reference video** - The system extracts motion trajectories from the reference video and applies them to the character/object in the reference image, generating a new video wi…

##### Kling-V3-Turbo

- [Kling-V3-Turbo Text to Video](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v3-turbo-text-to-video.md): - Kling-V3 Turbo Text to Video (kling-v3-turbo-text-to-video) model supports text-to-video generation - Resolution supports 720P / 1080P (4K not supported), duration 3 ~ 15 seconds - Supports single-shot and multi-shot modes (use the shot syntax in `prompt`) - Asynchronous processing mode, use the r…
- [Kling-V3-Turbo Image to Video](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-v3-turbo-image-to-video.md): - Kling-V3 Turbo Image to Video (kling-v3-turbo-image-to-video) model supports image-to-video generation - Generates video based on a first-frame image, resolution supports 720P / 1080P (4K not supported), duration 3 ~ 15 seconds - The aspect ratio is determined by the first-frame image, **`aspect_r…

##### Kling-O1

- [Kling-O1 Image to Video](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o1-image-to-video.md): - Kling-O1 Image to Video (kling-o1-image-to-video) model supports image-to-video generation - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly
- [Kling-O1 Video Edit](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o1-video-edit.md): - Kling-O1 Video Edit (kling-o1-video-edit) model supports video editing - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly
- [Kling-O1 Video Edit (Fast)](https://evolink.ai/docs/en/api-manual/video-series/kling/kling-o1-video-edit-fast.md): - Kling-O1 Video Edit Fast (kling-o1-video-edit-fast) model supports fast video editing - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly

#### HappyHorse

##### HappyHorse 1.1

- [HappyHorse 1.1 Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.1/happyhorse-1.1-text-to-video.md): - HappyHorse 1.1 text-to-video, generates video from a text prompt only - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly
- [HappyHorse 1.1 Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.1/happyhorse-1.1-image-to-video.md): - HappyHorse 1.1 image-to-video, generates video from a single first-frame image - `prompt` is optional (when omitted, the first frame drives free interpretation) - Output aspect ratio is auto-determined by the first frame; **does not support** `aspect_ratio` - Asynchronous processing mode, use the…
- [HappyHorse 1.1 Reference-to-Video](https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.1/happyhorse-1.1-reference-to-video.md): - HappyHorse 1.1 reference-to-video, supports 1–9 reference images plus a text prompt - **Character reference convention**: in `prompt`, use `character1`, `character2`, `character3` ... keywords to reference the images in `image_urls` array in order - Asynchronous processing mode, use the returned t…

##### HappyHorse 1.0

- [HappyHorse 1.0 Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-text-to-video.md): - HappyHorse 1.0 text-to-video, generates video from a text prompt only - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly
- [HappyHorse 1.0 Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-image-to-video.md): - HappyHorse 1.0 image-to-video, generates video from a single first-frame image - `prompt` is optional (when omitted, the first frame drives free interpretation) - Output aspect ratio is auto-determined by the first frame; **does not support** `aspect_ratio` - Asynchronous processing mode, use the…
- [HappyHorse 1.0 Reference-to-Video](https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-reference-to-video.md): - HappyHorse 1.0 reference-to-video, supports 1–9 reference images plus a text prompt - **Character reference convention**: in `prompt`, use `character1`, `character2`, `character3` ... keywords to reference the images in `image_urls` array in order - Asynchronous processing mode, use the returned t…
- [HappyHorse 1.0 Video-Edit](https://evolink.ai/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-video-edit.md): - HappyHorse 1.0 video edit, takes 1 source video and text instructions to perform style transfer, local replacement, etc. - Optionally accepts 0–5 reference images for style / subject guidance - **Does not support** `duration`: output video duration = `min(input video duration, 15)`, determined by…

#### Grok

- [Grok Imagine 1.5 Video Preview](https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-video-1.5-preview.md): - Grok Imagine 1.5 (grok-imagine-video-1.5-preview) supports text-to-video, image-to-video and reference-to-video under one model name - There is no mode parameter: the number of entries in `image_urls` selects the mode — `0` = text-to-video, `1` = image-to-video (used as the first frame), `2`-`7` =…
- [Grok Imagine 1.0 Text to Video](https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-video-1.0-t2v.md): - Grok Imagine 1.0 (grok-imagine-video-1.0-t2v) model supports text-to-video mode - This model accepts text input only; passing `image_urls` returns an error. For image-to-video, use [grok-imagine-video-1.0-i2v](/en/api-manual/video-series/grok/grok-imagine-video-1.0-i2v) - Asynchronous processing m…
- [Grok Imagine 1.0 Image to Video](https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-video-1.0-i2v.md): - Grok Imagine 1.0 (grok-imagine-video-1.0-i2v) model supports image-to-video mode - `image_urls` is required and supports `1` ~ `7` images per request; omitting it or passing more than `7` returns an error. For text-to-video, use [grok-imagine-video-1.0-t2v](/en/api-manual/video-series/grok/grok-im…
- [Grok Imagine Text to Video Beta](https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-text-to-video.md): - Grok Imagine (grok-imagine-text-to-video-beta) model supports text-to-video mode - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly
- [Grok Imagine Image to Video Beta](https://evolink.ai/docs/en/api-manual/video-series/grok/grok-imagine-image-to-video.md): - Grok Imagine (grok-imagine-image-to-video-beta) model supports image-to-video mode - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly

#### Seedance

- [Seedance-1.5-Pro Video Generation](https://evolink.ai/docs/en/api-manual/video-series/seedance1.5/seedance-1.5-pro-video-generate.md): - Seedance 1.5 Pro (seedance-1.5-pro) model supports multiple generation modes including text-to-video, image-to-video, and first-last-frame - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 ho…
- [Seedance-1.0-Pro-Fast Video Generation](https://evolink.ai/docs/en/api-manual/video-series/seedance1.0/seedance-1.0-pro-fast-video-generate.md): - Seedance 1.0 Pro Fast (doubao-seedance-1.0-pro-fast) model supports multiple generation modes including text-to-video and image-to-video - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hour…

#### Sora2

- [Sora-2 Video Generation](https://evolink.ai/docs/en/api-manual/video-series/sora2/sora-2-preview-video-generate.md): - Sora 2 Preview (sora-2-preview) supports text-to-video, image-to-video and more - Async processing, use returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save promptly
- [Sora-2-Pro Video Generation](https://evolink.ai/docs/en/api-manual/video-series/sora2pro/sora-2-pro-preview-video-generate.md): - Sora 2 Pro (sora-2-pro-preview) model supports text-to-video, image-to-video and other modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly

#### Veo3.1

- [Veo3.1-Pro Video Generation](https://evolink.ai/docs/en/api-manual/video-series/veo3.1/veo-3.1-generate-preview-generate.md): - Veo 3.1 Generate Preview supports text-to-video, first-frame image-to-video and more - Async processing, use returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours
- [Veo3.1-Pro Video Generation Beta](https://evolink.ai/docs/en/api-manual/video-series/veo3.1/veo3.1-pro-video-generate.md): - Veo 3.1 Pro (veo3.1-pro-beta) model supports text-to-video, first-and-last-frame image-to-video and other modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promp…
- [Veo3.1-Fast Video Generation](https://evolink.ai/docs/en/api-manual/video-series/veo3.1/veo-3.1-fast-generate-preview-generate.md): - Veo 3.1 Fast Generate Preview supports text-to-video, first-frame image-to-video and more - Async processing, use returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save promptly
- [Veo3.1-Fast Video Generation Beta](https://evolink.ai/docs/en/api-manual/video-series/veo3.1/veo3.1-fast-video-generate.md): - Veo 3.1 Fast (veo-3.1-fast) model supports text-to-video, first-frame image-to-video and other modes - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly

#### Hailuo

- [Hailuo-02 Video Generation](https://evolink.ai/docs/en/api-manual/video-series/hailuo/hailuo-02-video-generate.md): - Hailuo 02 (MiniMax-Hailuo-02) supports T2V (Text-to-Video), I2V (Image-to-Video) and FLF (First-Last-Frame) modes - Auto mode detection: 0 images=T2V, 1 image=I2V, 2 images=FLF - Full-featured model, supports 512P resolution (I2V mode only) - Supports 15 camera motion commands like `[Pan left]`, `…
- [Hailuo-2.3 Video Generation](https://evolink.ai/docs/en/api-manual/video-series/hailuo/hailuo-2-3-video-generate.md): - Hailuo 2.3 (MiniMax-Hailuo-2.3) supports T2V (Text-to-Video) and I2V (Image-to-Video) modes - Auto mode detection: 0 images=T2V, 1 image=I2V - SOTA instruction following, high-quality output - Supports 15 camera motion commands like `[Pan left]`, `[Push in]`, `[Static shot]` - Async processing, us…
- [Hailuo-2.3-Fast Video Generation](https://evolink.ai/docs/en/api-manual/video-series/hailuo/hailuo-2-3-fast-video-generate.md): - Hailuo 2.3 Fast (MiniMax-Hailuo-2.3-Fast) supports I2V (Image-to-Video) mode only - Fastest generation speed, ultimate physics effects - Supports 15 camera motion commands like `[Pan left]`, `[Push in]`, `[Static shot]` - Async processing, use returned task ID to [query status](/en/api-manual/task…

#### Wan

##### Wan3.0

- [Wan3.0 Complete Parameter Guide](https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-overview.md): Unified API for Wan 3.0 (all-round reference video); select the mode and edition with the `model` parameter
- [Wan3.0 Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-text-to-video.md): - Generates video from `prompt` only, **no media input is accepted** - Videos of up to **30 seconds**, `duration: -1` smart duration supported - For first-and-last-frame control use [Wan3.0 Image-to-Video](/en/api-manual/video-series/wan3.0/wan3.0-image-to-video); for reference material use [Wan3.0…
- [Wan3.0 Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-image-to-video.md): - Pass `image_start` to strictly set the video's **first frame**; add `image_end` to strictly set the **last frame** as well - **Reference material is not accepted** (reference videos / reference audio / files / web pages): first-and-last frames and reference material are mutually exclusive. For mix…
- [Wan3.0 Reference-to-Video](https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-reference-video.md): - Reference images / reference videos / reference audio / files / web pages serve as material; the model interprets the intent automatically and generates the video - Refer to the material in the prompt as "Image 1", "Video 1" and "Audio 1"; **the three material types are counted independently** - `…
- [Wan3.0 Prime Text-to-Video](https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-prime-text-to-video.md): - Generates video from `prompt` only, **no media input is accepted** - Videos of up to **30 seconds**, `duration: -1` smart duration supported - For first-and-last-frame control use [Wan3.0 Prime Image-to-Video](/en/api-manual/video-series/wan3.0/wan3.0-prime-image-to-video); for reference material…
- [Wan3.0 Prime Image-to-Video](https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-prime-image-to-video.md): - Pass `image_start` to strictly set the video's **first frame**; add `image_end` to strictly set the **last frame** as well - **Reference material is not accepted** (reference videos / reference audio / files / web pages): first-and-last frames and reference material are mutually exclusive. For mix…
- [Wan3.0 Prime Reference-to-Video](https://evolink.ai/docs/en/api-manual/video-series/wan3.0/wan3.0-prime-reference-video.md): - Reference images / reference videos / reference audio / files / web pages serve as material; the model interprets the intent automatically and generates the video - Refer to the material in the prompt as "Image 1", "Video 1" and "Audio 1"; **the three material types are counted independently** - `…

##### Wan2.7

- [Wan2.7 Text to Video](https://evolink.ai/docs/en/api-manual/video-series/wan2.7/wan2.7-text-to-video.md): - WAN2.7 (wan2.7-text-to-video) model supports text-to-video generation, producing fluent videos from textual prompts - **Multi-shot narrative:** Control shot structure via natural language in `prompt`   - Single shot: state "generate a single-shot video" in the prompt   - Multi shot: use "generate…
- [Wan2.7 Image to Video](https://evolink.ai/docs/en/api-manual/video-series/wan2.7/wan2.7-image-to-video.md): - WAN2.7 (wan2.7-image-to-video) model supports image-to-video generation with multimodal inputs (image / audio / video) - Choose one of three generation modes via the `generation_mode` parameter:   - `first_frame`: **First-frame to video** — generate a video starting from the given first frame, opt…
- [Wan2.7 Reference Video](https://evolink.ai/docs/en/api-manual/video-series/wan2.7/wan2.7-reference-video.md): - WAN2.7 (wan2.7-reference-video) model supports reference-to-video generation, using people or objects as protagonists to produce single-character performances or multi-character interactions - Multimodal inputs: starting frame (`image_start`), multiple reference images (`image_urls`), multiple ref…
- [Wan2.7 Video Edit](https://evolink.ai/docs/en/api-manual/video-series/wan2.7/wan2.7-video-edit.md): - WAN2.7 (wan2.7-video-edit) model supports video editing for **instruction-based editing** and **video transfer** tasks - **Required:** upload exactly 1 video (`video_urls`); optionally upload up to 4 reference images (`image_urls`) - Two usage patterns:   - **Instruction-only editing:** provide `v…

##### Wan2.6

- [Wan2.6 Text to Video](https://evolink.ai/docs/en/api-manual/video-series/wan2.6/wan2.6-text-to-video.md): - WAN2.6 (wan2.6-text-to-video) model supports text-to-video generation - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly
- [Wan2.6 Image to Video](https://evolink.ai/docs/en/api-manual/video-series/wan2.6/wan2.6-image-to-video.md): - WAN2.6 (wan2.6-image-to-video) model supports first-frame image-to-video generation - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly
- [Wan2.6 Image-to-Video Flash](https://evolink.ai/docs/en/api-manual/video-series/wan2.6/wan2.6-image-to-video-flash.md): - WAN2.6 Flash (wan2.6-image-to-video-flash) model supports first-frame image-to-video generation with faster speed - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save t…
- [Wan2.6 Reference Video](https://evolink.ai/docs/en/api-manual/video-series/wan2.6/wan2.6-reference-video.md): - WAN2.6 (wan2.6-reference-video) model supports reference video-to-video generation - Upload reference videos, the model will extract character appearance and voice to generate new videos - Asynchronous processing mode, use the returned task ID to [query status](/en/api-manual/task-management/get-t…
- [Wan2.6 Reference Video Flash](https://evolink.ai/docs/en/api-manual/video-series/wan2.6/wan2.6-reference-video-flash.md): - WAN2.6 Flash (wan2.6-reference-video-flash) model supports reference video generation with faster speed - Upload reference videos, the model will reference character appearance and voice from the videos to generate new videos - Asynchronous processing mode, use the returned task ID to [query statu…

##### Wan2.5

- [Wan2.5 Text to Video](https://evolink.ai/docs/en/api-manual/video-series/wan2.5/wan2.5-text-to-video.md): - WAN2.5 (wan2.5-text-to-video) model supports text-to-video mode - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly
- [Wan2.5 Image to Video](https://evolink.ai/docs/en/api-manual/video-series/wan2.5/wan2.5-image-to-video.md): - WAN2.5 (wan2.5-image-to-video) model supports first-frame image-to-video mode - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly

#### OmniHuman

- [OmniHuman-1.5 Digital Human Video Generation](https://evolink.ai/docs/en/api-manual/video-series/omnihuman/omnihuman-1.5-video-generate.md): - OmniHuman-1.5 (omnihuman-1.5) model generates digital human videos driven by audio - Asynchronous processing mode, use the returned task ID to [query](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours, please save them promptly

#### VideoRetalk

- [VideoRetalk Video Generate](https://evolink.ai/docs/en/api-manual/video-series/videoretalk/videoretalk-video-generate.md): - Audio-driven lip-sync video generation — replaces the lip movements of the person in the video with ones matching the target audio - Asynchronous processing mode; use the returned task ID to [query the result](/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24…

#### Topaz

- [Topaz Video Upscale](https://evolink.ai/docs/en/api-manual/video-series/topaz/topaz-video-upscale.md): - Topaz Video Upscale (topaz-video-upscale) model supports AI-powered video super-resolution upscaling - Supports 1x (enhancement only), 2x, and 4x upscale factors - Billing is based on input video duration (per second) and upscale factor - Asynchronous processing mode, use the returned task ID to […

### Audio Series

#### Seed Audio

- [Seed-Audio 1.0 Voices](https://evolink.ai/docs/en/api-manual/audio-series/doubao-seed-audio/doubao-seed-audio-1-0-voices.md)
- [Seed-Audio 1.0 Audio Generation](https://evolink.ai/docs/en/api-manual/audio-series/doubao-seed-audio/doubao-seed-audio-1-0.md): - Multimodal audio generation with three modes: **text-to-audio**, **reference-audio (voice cloning)**, and **reference-image** - Up to `120` seconds of audio per request - Asynchronous mode — use the returned task ID to [query the result](/en/api-manual/task-management/get-task-detail) - Generated…

#### Suno

- [Suno Music Generation Beta](https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-music-generation.md): - Suno AI music generation model, supports generating complete music based on text descriptions or lyrics - Supports custom mode (fine control over style, title, lyrics) and simple mode (AI auto-generation) - Supports [Persona](/en/api-manual/audio-series/suno/suno-persona-creation) for reusable voc…
- [Suno Persona Creation Beta](https://evolink.ai/docs/en/api-manual/audio-series/suno/suno-persona-creation.md): - Extract reusable Persona (vocal/style characteristics) from completed Suno music generation tasks - After successful creation, a `persona_id` is returned, which can be applied in subsequent [Suno Music Generation](/en/api-manual/audio-series/suno/suno-music-generation) via `persona_id` and `person…

#### Qwen TTS

- [Qwen Voice Design](https://evolink.ai/docs/en/api-manual/audio-series/qwen-tts/qwen-voice-design.md): - Create a custom voice profile from a text description and receive the voice name and a preview audio clip - [Qwen3 TTS VD](/en/api-manual/audio-series/qwen-tts/qwen3-tts-vd) speech synthesis **must use a voice created by this API** — system built-in voices are not supported - Asynchronous processi…
- [Qwen3 TTS VD](https://evolink.ai/docs/en/api-manual/audio-series/qwen-tts/qwen3-tts-vd.md): - Convert text to speech audio; **must use a custom voice created with [Qwen Voice Design](/en/api-manual/audio-series/qwen-tts/qwen-voice-design)** — system built-in voices are not supported - Workflow: call `qwen-voice-design` to create a voice → obtain the `voice` name → pass it to the `voice` pa…

### Text Series

#### EvoLink Auto

- [EvoLink Auto - Smart Model Routing](https://evolink.ai/docs/en/api-manual/language-series/evolink-auto/evolink-auto-quickstart.md): The system automatically selects the most suitable model to process the request
- [EvoLink Auto - Claude Format](https://evolink.ai/docs/en/api-manual/language-series/evolink-auto/evolink-auto-claude.md): Intelligent routing using Anthropic Messages API format
- [EvoLink Auto - Gemini Format](https://evolink.ai/docs/en/api-manual/language-series/evolink-auto/evolink-auto-gemini.md): Intelligent routing using Google Generative AI format

#### EvoLink Moderation

- [EvoLink Moderation 1.0 - Complete API Reference](https://evolink.ai/docs/en/api-manual/language-series/evolink-moderation-1.0/evolink-moderation-1.0-api.md): - Synchronous endpoint that detects harmful content across 13 dimensions for the input **text** and/or **image** - The response returns a unified summary via the `evolink_summary` field with `risk_level` / `flagged` / `violations` / `max_score` / `max_category`

#### Kimi

##### Kimi K3

###### Chat Completions API

- [Kimi K3 - OpenAI-Compatible API](https://evolink.ai/docs/en/api-manual/language-series/kimi-k3/kimi-k3-chat.md): Call `kimi-k3` through the OpenAI Chat Completions protocol. Supports both non-streaming JSON and streaming SSE responses. K3 always performs reasoning, and `reasoning_effort` currently supports only `max`.

###### Messages API

- [Kimi K3 - Anthropic-Compatible API](https://evolink.ai/docs/en/api-manual/language-series/kimi-k3/kimi-k3-messages.md): Call `kimi-k3` through the Anthropic Messages protocol. Supports both non-streaming JSON and Anthropic SSE event streams.

#### Claude

- [Claude - Messages API](https://evolink.ai/docs/en/api-manual/language-series/claude/claude-messages-api.md): - Send a structured list of input messages with text and/or image content, and the model will generate the next message in the conversation. - The Messages API can be used for either single queries or stateless multi-turn conversations.

#### Gemini

##### Google Native API Format

- [Gemini All-Model API - Native API Quickstart](https://evolink.ai/docs/en/api-manual/language-series/gemini/native-api/native-api-quickstart.md): - Call Gemini text models using the Google native API format - Select the specific model via `{model}` in the path (see the `model` parameter for all available values) - Synchronous processing mode, minimal parameters, quick to get started - Need more features? See the [full parameter documentation]…
- [Gemini All-Model API - Native API Format](https://evolink.ai/docs/en/api-manual/language-series/gemini/native-api/native-api-reference.md): Select the Gemini text model to call via `{model}` in the path (see the reference table for the `model` parameter for all available values).

##### OpenAI SDK Format

- [Gemini All-Model API - OpenAI Quickstart](https://evolink.ai/docs/en/api-manual/language-series/gemini/openai-sdk/openai-sdk-quickstart.md): - Call Gemini text models using the OpenAI SDK format - Select the specific model via the `model` parameter (see the `model` parameter for all available values) - Synchronous processing mode, minimal parameters, quick to get started - Need more features? See the [full parameter documentation](./open…
- [Gemini All-Model API - OpenAI-Compatible Format](https://evolink.ai/docs/en/api-manual/language-series/gemini/openai-sdk/openai-sdk-reference.md): Select the Gemini text model to call via `model` in the request body (see the reference table for the `model` parameter for all available values).

#### GPT

##### Chat Completions API

- [GPT All-Model API - Chat Completions Quickstart](https://evolink.ai/docs/en/api-manual/language-series/gpt/chat-completions/chat-completions-quickstart.md): - Call GPT series text models using the OpenAI SDK format (select the specific model via the `model` parameter) - Reasoning + tool-calling models, supporting mixed text and image input - Synchronous processing mode, minimal parameters, quick to get started - Need more parameters? See the [full param…
- [GPT All-Model API - Chat Completions Reference](https://evolink.ai/docs/en/api-manual/language-series/gpt/chat-completions/chat-completions-reference.md): - OpenAI-compatible Chat Completions API for GPT series text models; select the specific model via `model` (see the comparison table on the `model` parameter for all allowed values) - The whole series consists of reasoning models, with reasoning depth controlled by `reasoning_effort`; reasoning toke…

##### Responses API

- [GPT All-Model API - Responses Quickstart](https://evolink.ai/docs/en/api-manual/language-series/gpt/responses/responses-quickstart.md): - Call GPT series text models using the OpenAI Responses format (select the specific model via the `model` parameter) - Reasoning + tool-calling models, supporting mixed text and image input - This API supports server-side tools: web search, code execution, and file search - Multi-turn conversations…
- [GPT All-Model API - Responses Reference](https://evolink.ai/docs/en/api-manual/language-series/gpt/responses/responses-reference.md): - OpenAI-compatible Responses API for GPT series text models; select the specific model via `model` (see the comparison table on the `model` parameter for all allowed values) - The whole series consists of reasoning models, with reasoning depth controlled by `reasoning.effort`; reasoning tokens are…

#### Grok

##### Chat Completions API

- [Grok All-Model API - Chat Completions Quickstart](https://evolink.ai/docs/en/api-manual/language-series/grok/chat-completions/chat-completions-quickstart.md): - Call xAI Grok text models using the OpenAI SDK format (pick the model via the `model` parameter) - Reasoning + tool-use models with a 500K-token context window - Synchronous processing mode, minimal parameters, quick to get started - Need more features? See the [full parameter documentation](./cha…
- [Grok All-Model API - Chat Completions Reference](https://evolink.ai/docs/en/api-manual/language-series/grok/chat-completions/chat-completions-reference.md): - OpenAI-compatible Chat Completions endpoint for xAI Grok text models; pick the model via the `model` parameter (see the table on the `model` parameter for all values) - 500K-token context window; prompts of 200K tokens or more are billed at 2x for all token types - Prompt caching is automatic: cac…

##### Responses API

- [Grok All-Model API - Responses Quickstart](https://evolink.ai/docs/en/api-manual/language-series/grok/responses/responses-quickstart.md): - Call xAI Grok text models using the OpenAI Responses API format (pick the model via the `model` parameter) - Reasoning + tool-use models with a 500K-token context window - This endpoint unlocks xAI server-side tools: web search, X search, code execution, attachment search, and collections search (…
- [Grok All-Model API - Responses Reference](https://evolink.ai/docs/en/api-manual/language-series/grok/responses/responses-reference.md): - OpenAI-compatible Responses endpoint for xAI Grok text models; pick the model via the `model` parameter (see the table on the `model` parameter for all values) - 500K-token context window; prompts of 200K tokens or more are billed at 2x for all token types - Prompt caching is automatic: cached pro…

#### Doubao Seed 2.0

##### Chat Completions API

- [Doubao Seed 2.0 - Quick Start](https://evolink.ai/docs/en/api-manual/language-series/doubao-seed-2.0/doubao-seed-2.0-quickstart.md): - Call Doubao Seed 2.0 series models using OpenAI SDK format - Synchronous processing mode, returns chat content in real time - Minimized parameters for quick start - Supported models: `doubao-seed-2.0-pro`, `doubao-seed-2.0-lite`, `doubao-seed-2.0-mini`, `doubao-seed-2.0-code` - Need more features?…
- [Doubao Seed 2.0 - Complete API Reference](https://evolink.ai/docs/en/api-manual/language-series/doubao-seed-2.0/doubao-seed-2.0-reference.md): - Call Doubao Seed 2.0 series models using OpenAI SDK format - Synchronous processing mode, real-time response - **Text Chat**: Single or multi-turn contextual conversation - **System Prompts**: Customize AI role and behavior - **Multimodal Input**: Supports text + image + video mixed input - **Deep…

##### Responses API

- [Doubao Seed 2.0 Responses API - Quick Start](https://evolink.ai/docs/en/api-manual/language-series/doubao-seed-2.0/doubao-seed-2.0-responses-quickstart.md): - Use Responses API format to call Doubao Seed 2.0 series models - Supports server-side context storage, enabling multi-turn conversations via `previous_response_id` - Minimal parameters, quick start - Supported models: `doubao-seed-2.0-pro`, `doubao-seed-2.0-lite`, `doubao-seed-2.0-mini`, `doubao-s…
- [Doubao Seed 2.0 Responses API - Complete API Reference](https://evolink.ai/docs/en/api-manual/language-series/doubao-seed-2.0/doubao-seed-2.0-responses-reference.md): - Use Responses API format to call Doubao Seed 2.0 series models - **Server-side context storage**: Implement multi-turn conversations via `previous_response_id`, no need to manually pass conversation history - **Multimodal input**: Supports text + image + video + file (PDF) mixed input - **Deep thi…

#### DeepSeek

##### DeepSeek V4

###### Chat Completions API

- [DeepSeek V4 - OpenAI-Compatible API](https://evolink.ai/docs/en/api-manual/language-series/deepseek-v4/deepseek-v4-chat.md): - Call the DeepSeek V4 model using the OpenAI Chat Completions protocol - Supports three models: `deepseek-v4-flash` (fast general-purpose), `deepseek-v4-pro` (deep reasoning), and `deepseek-v4-flash-vision-exp` (image understanding) - **Plain text conversation**: Single- or multi-turn contextual di…

###### Messages API

- [DeepSeek V4 - Anthropic-Compatible API](https://evolink.ai/docs/en/api-manual/language-series/deepseek-v4/deepseek-v4-messages.md): - Invoke DeepSeek V4 models using the Anthropic Messages protocol - Supports `deepseek-v4-flash` / `deepseek-v4-pro` / `deepseek-v4-flash-vision-exp` - Request / response structures aligned with the Anthropic API - **Image understanding**: `deepseek-v4-flash-vision-exp` supports `image` content bloc…

###### Responses API

- [DeepSeek V4 - Responses API](https://evolink.ai/docs/en/api-manual/language-series/deepseek-v4/deepseek-v4-responses.md): - Call DeepSeek V4 models using the OpenAI Responses protocol - Supports three models: `deepseek-v4-flash` (fast general-purpose), `deepseek-v4-pro` (deep reasoning), and `deepseek-v4-flash-vision-exp` (image understanding) - **Input shapes**: `input` can be plain text or an array of input items (me…

##### DeepSeek V3.2

- [DeepSeek - Complete API Reference](https://evolink.ai/docs/en/api-manual/language-series/deepseek/deepseek-reference.md): - Call DeepSeek models using OpenAI SDK format - Synchronous processing mode, real-time response - Supports `deepseek-chat` (general conversation) and `deepseek-reasoner` (deep reasoning) models - **Text Chat**: Single or multi-turn contextual conversation - **System Prompts**: Customize AI role and…

#### MiniMax

##### MiniMax-M3

###### Chat Completions API

- [MiniMax-M3 - OpenAI-Compatible API](https://evolink.ai/docs/en/api-manual/language-series/minimax-m3/minimax-m3-chat.md): - Use the OpenAI Chat Completions protocol to call the MiniMax-M3 model - **Multi-turn conversation**: Supports single-turn or multi-turn contextual dialogue - **System prompts**: Customize AI role and behavior via `role=system` messages - **Multimodal input**: `content` supports mixed text + image…

###### Messages API

- [MiniMax-M3 - Anthropic-Compatible API](https://evolink.ai/docs/en/api-manual/language-series/minimax-m3/minimax-m3-messages.md): - Use the Anthropic Messages protocol to call the MiniMax-M3 model - Request / response structure aligns with the Anthropic API - **Multimodal conversation**: `content` supports text and image content blocks - **System prompts**: Passed via the top-level `system` field - **Thinking mode**: Controlle…

##### MiniMax-M2.5

- [MiniMax-M2.5 - Complete API Reference](https://evolink.ai/docs/en/api-manual/language-series/minimax-m2.5/minimax-m2.5-api.md): - Use OpenAI SDK format to call MiniMax-M2.5 model - Synchronous processing mode, real-time response - **Text conversation**: Single or multi-turn contextual dialogue - **System prompts**: Customize AI role and behavior

#### Qwen

##### Qwen3.8-Max

###### Chat Completions API

- [Qwen3.8-Max - Full Parameter Documentation](https://evolink.ai/docs/en/api-manual/language-series/qwen3.8-max/qwen3.8-max-chat.md): - Call Qwen3.8-Max using the OpenAI Chat Completions protocol - **Multi-turn conversation**: supports single-turn or multi-turn contextual conversations - **System prompt**: set the AI's role and behavior via a `role=system` message - **Multimodal input**: pass a content part array in `content`, sup…

###### Responses API

- [Qwen3.8-Max - Responses API](https://evolink.ai/docs/en/api-manual/language-series/qwen3.8-max/qwen3.8-max-responses.md): - Call Qwen3.8-Max using the OpenAI Responses protocol - **Flexible input**: `input` can be a string or a Chat-format message array (supporting multimodal `input_text` / `input_image`) - **Multi-turn conversation**: pass `previous_response_id` to link to the previous response, and the server automat…

###### Messages API

- [Qwen3.8-Max - Anthropic-Compatible API](https://evolink.ai/docs/en/api-manual/language-series/qwen3.8-max/qwen3.8-max-messages.md): - Call Qwen3.8-Max using the Anthropic Messages protocol - **System prompt**: set via the top-level `system` field (not inside messages) - **Multimodal input**: pass a content block array in `content`, supporting `text` / `image` - **Context caching**: add `cache_control` on a content block to decla…

#### GLM

##### Chat Completions API

- [GLM All-Model API - Chat Completions Quickstart](https://evolink.ai/docs/en/api-manual/language-series/glm/chat-completions/chat-completions-quickstart.md): - Call GLM series models through the OpenAI Chat Completions protocol, choosing the specific model with the `model` parameter - `model` and `messages` are the only parameters you need - 1M token context window across the series, with up to 131,072 output tokens - Deep thinking is on by default acros…
- [GLM All-Model API - Chat Completions Reference](https://evolink.ai/docs/en/api-manual/language-series/glm/chat-completions/chat-completions-reference.md): - Call GLM series models through the OpenAI Chat Completions protocol, choosing the specific model with the `model` parameter - Synchronous processing that returns the conversation content in real time - **Text conversation**: single-turn or multi-turn contextual conversation; `glm-5.3-flash` additi…

##### Messages API

- [GLM All-Model API - Messages Quickstart](https://evolink.ai/docs/en/api-manual/language-series/glm/messages/messages-quickstart.md): - Call GLM series models through the Anthropic Messages protocol, choosing the specific model with the `model` parameter - `model`, `max_tokens` and `messages` are the only parameters you need (`max_tokens` is mandatory in the Anthropic protocol) - 1M token context window across the series, with up…
- [GLM All-Model API - Messages Reference](https://evolink.ai/docs/en/api-manual/language-series/glm/messages/messages-reference.md): - Call GLM series models through the Anthropic Messages protocol, choosing the specific model with the `model` parameter - The request and response structures match the Anthropic API - **System prompt**: passed through the top-level `system` field - **Thinking mode**: thinking is on by default acros…

### Account Management

- [Get Credits Usage](https://evolink.ai/docs/en/api-manual/account-management/get-credits.md): Query the current user and token credit balance and usage information

### Task Management

- [Error Codes Reference](https://evolink.ai/docs/en/api-manual/task-management/error-codes.md): Complete list of task error codes and troubleshooting guide
- [Query Task Status](https://evolink.ai/docs/en/api-manual/task-management/get-task-detail.md): Query the status, progress, and result information of asynchronous tasks by task ID

### File Management

- [Get File Quota](https://evolink.ai/docs/en/api-manual/file-series/quota.md): - Query current user's file usage and remaining quota - Default user group allows up to `2000` files

#### File Upload

- [Base64 File Upload](https://evolink.ai/docs/en/api-manual/file-series/upload-base64.md): - Supports Base64 encoding and Data URL formats - Automatically identifies file types and categorizes storage - Returns accessible file URLs and download links - Files will expire after 72 hours - Current user quota is limited. Uploads will fail when quota is exhausted. Please save locally if persis…
- [File Stream Upload](https://evolink.ai/docs/en/api-manual/file-series/upload-stream.md): - Upload files using multipart/form-data format - Supports both underscore and camelCase parameter naming - Suitable for uploading local files directly - Files will expire after 72 hours - Current user quota is limited. Uploads will fail when quota is exhausted. Please save locally if persistent sto…
- [URL File Upload](https://evolink.ai/docs/en/api-manual/file-series/upload-url.md): - Upload by providing a remote file URL - System will automatically download and store the remote file - Suitable for migrating files from other servers - Files will expire after 72 hours - Current user quota is limited. Uploads will fail when quota is exhausted. Please save locally if persistent st…

## OpenAPI Specs

- [nanobanana-2-lite-image-generate](/docs/en/api-manual/image-series/nanobanana/nanobanana-2-lite-image-generate.json)
- [nanobanana-2-lite-beta-image-generate](/docs/en/api-manual/image-series/nanobanana/nanobanana-2-lite-beta-image-generate.json)
- [nanobanana-2-image-generate](/docs/en/api-manual/image-series/nanobanana/nanobanana-2-image-generate.json)
- [nanobanana-2-beta-image-generate](/docs/en/api-manual/image-series/nanobanana/nanobanana-2-beta-image-generate.json)
- [nanobanana-pro-image-generate](/docs/en/api-manual/image-series/nanobanana/nanobanana-pro-image-generate.json)
- [nanobanana-pro-beta-image-generate](/docs/en/api-manual/image-series/nanobanana/nanobanana-pro-beta-image-generate.json)
- [nanobanana-image-generate](/docs/en/api-manual/image-series/nanobanana/nanobanana-image-generate.json)
- [grok-imagine-image-2.0-image-generate](/docs/en/api-manual/image-series/grok/grok-imagine-image-2.0-image-generate.json)
- [mj-v8-1-image-generate](/docs/en/api-manual/image-series/midjourney/mj-v8-1-image-generate.json)
- [mj-v8-1-variation](/docs/en/api-manual/image-series/midjourney/mj-v8-1-variation.json)
- [mj-v8-1-remix](/docs/en/api-manual/image-series/midjourney/mj-v8-1-remix.json)
- [mj-v8-1-retexture](/docs/en/api-manual/image-series/midjourney/mj-v8-1-retexture.json)
- [mj-v8-1-upload-paint](/docs/en/api-manual/image-series/midjourney/mj-v8-1-upload-paint.json)
- [mj-v8-1-edit](/docs/en/api-manual/image-series/midjourney/mj-v8-1-edit.json)
- [mj-v8-1-remove-bg](/docs/en/api-manual/image-series/midjourney/mj-v8-1-remove-bg.json)
- [mj-v7-image-generate](/docs/en/api-manual/image-series/midjourney/mj-v7-image-generate.json)
- [mj-v7-variation](/docs/en/api-manual/image-series/midjourney/mj-v7-variation.json)
- [mj-v7-upscale](/docs/en/api-manual/image-series/midjourney/mj-v7-upscale.json)
- [mj-v7-remix](/docs/en/api-manual/image-series/midjourney/mj-v7-remix.json)
- [mj-v7-enhance](/docs/en/api-manual/image-series/midjourney/mj-v7-enhance.json)
- [mj-v7-pan](/docs/en/api-manual/image-series/midjourney/mj-v7-pan.json)
- [mj-v7-outpaint](/docs/en/api-manual/image-series/midjourney/mj-v7-outpaint.json)
- [mj-v7-inpaint](/docs/en/api-manual/image-series/midjourney/mj-v7-inpaint.json)
- [mj-v7-edit](/docs/en/api-manual/image-series/midjourney/mj-v7-edit.json)
- [mj-v7-remove-bg](/docs/en/api-manual/image-series/midjourney/mj-v7-remove-bg.json)
- [mj-v7-retexture](/docs/en/api-manual/image-series/midjourney/mj-v7-retexture.json)
- [mj-v7-upload-paint](/docs/en/api-manual/image-series/midjourney/mj-v7-upload-paint.json)
- [gpt-image-2-image-generation](/docs/en/api-manual/image-series/gpt-image-2/gpt-image-2-image-generation.json)
- [gpt-image-2-beta-image-generation](/docs/en/api-manual/image-series/gpt-image-2/gpt-image-2-beta-image-generation.json)
- [gpt-image-1.5-image-generation](/docs/en/api-manual/image-series/gpt-image-1.5/gpt-image-1.5-image-generation.json)
- [seedream-5.0-pro-image-generate](/docs/en/api-manual/image-series/seedream/seedream-5.0-pro-image-generate.json)
- [seedream-5.0-pro-layerize-image-generate](/docs/en/api-manual/image-series/seedream/seedream-5.0-pro-layerize-image-generate.json)
- [seedream-5.0-lite-image-generate](/docs/en/api-manual/image-series/seedream/seedream-5.0-lite-image-generate.json)
- [seedream-4.5-image-generate](/docs/en/api-manual/image-series/seedream/seedream-4.5-image-generate.json)
- [seedream-4.0-image-generate](/docs/en/api-manual/image-series/seedream/seedream-4.0-image-generate.json)
- [z-image-turbo-image-generate](/docs/en/api-manual/image-series/z-image-turbo/z-image-turbo-image-generate.json)
- [qwen-image-3.0](/docs/en/api-manual/image-series/qwen/qwen-image-3.0.json)
- [qwen-image-3.0-pro](/docs/en/api-manual/image-series/qwen/qwen-image-3.0-pro.json)
- [qwen-image-edit-plus](/docs/en/api-manual/image-series/qwen/qwen-image-edit-plus.json)
- [qwen-image-edit](/docs/en/api-manual/image-series/qwen/qwen-image-edit.json)
- [wan2.5-text-to-image](/docs/en/api-manual/image-series/wan2.5/wan2.5-text-to-image.json)
- [wan2.5-image-to-image](/docs/en/api-manual/image-series/wan2.5/wan2.5-image-to-image.json)
- [krea-2-turbo-image-generate](/docs/en/api-manual/image-series/krea/krea-2-turbo-image-generate.json)
- [seedance-2.5-overview](/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-overview.json)
- [seedance-2.5-text-to-video](/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-text-to-video.json)
- [seedance-2.5-image-to-video](/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-image-to-video.json)
- [seedance-2.5-reference-to-video](/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-reference-to-video.json)
- [seedance-2.5-video-edit](/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-video-edit.json)
- [seedance-2.5-video-extend](/docs/en/api-manual/video-series/seedance2.5/seedance-2.5-video-extend.json)
- [seedance-2.0-overview](/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-overview.json)
- [seedance-2.0-text-to-video](/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-text-to-video.json)
- [seedance-2.0-image-to-video](/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-image-to-video.json)
- [seedance-2.0-reference-to-video](/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-reference-to-video.json)
- [seedance-2.0-fast-text-to-video](/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-fast-text-to-video.json)
- [seedance-2.0-fast-image-to-video](/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-fast-image-to-video.json)
- [seedance-2.0-fast-reference-to-video](/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-fast-reference-to-video.json)
- [seedance-2.0-mini-text-to-video](/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-mini-text-to-video.json)
- [seedance-2.0-mini-image-to-video](/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-mini-image-to-video.json)
- [seedance-2.0-mini-reference-to-video](/docs/en/api-manual/video-series/seedance2.0/seedance-2.0-mini-reference-to-video.json)
- [minimax-h3-overview](/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-overview.json)
- [minimax-h3-max-text-to-video](/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-max-text-to-video.json)
- [minimax-h3-max-image-to-video](/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-max-image-to-video.json)
- [minimax-h3-text-to-video](/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-text-to-video.json)
- [minimax-h3-image-to-video](/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-image-to-video.json)
- [minimax-h3-reference-to-video](/docs/en/api-manual/video-series/minimax/minimax-h3/minimax-h3-reference-to-video.json)
- [gemini-omni-1.1-flash-overview](/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-overview.json)
- [gemini-omni-1.1-flash-text-to-video](/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-text-to-video.json)
- [gemini-omni-1.1-flash-image-to-video](/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-image-to-video.json)
- [gemini-omni-1.1-flash-reference-to-video](/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-reference-to-video.json)
- [gemini-omni-1.1-flash-video-edit](/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-video-edit.json)
- [gemini-omni-1.1-flash-video-extend](/docs/en/api-manual/video-series/gemini-omni-1.1-flash/gemini-omni-1.1-flash-video-extend.json)
- [gemini-omni-flash-text-to-video](/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-text-to-video.json)
- [gemini-omni-flash-image-to-video](/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-image-to-video.json)
- [gemini-omni-flash-reference-to-video](/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-reference-to-video.json)
- [gemini-omni-flash-video-edit](/docs/en/api-manual/video-series/gemini-omni-flash-1.0/gemini-omni-flash-video-edit.json)
- [kling-custom-element](/docs/en/api-manual/video-series/kling/kling-custom-element.json)
- [kling-o3-text-to-video](/docs/en/api-manual/video-series/kling/kling-o3-text-to-video.json)
- [kling-o3-image-to-video](/docs/en/api-manual/video-series/kling/kling-o3-image-to-video.json)
- [kling-o3-reference-to-video](/docs/en/api-manual/video-series/kling/kling-o3-reference-to-video.json)
- [kling-o3-video-edit](/docs/en/api-manual/video-series/kling/kling-o3-video-edit.json)
- [kling-v3-text-to-video](/docs/en/api-manual/video-series/kling/kling-v3-text-to-video.json)
- [kling-v3-image-to-video](/docs/en/api-manual/video-series/kling/kling-v3-image-to-video.json)
- [kling-v3-motion-control](/docs/en/api-manual/video-series/kling/kling-v3-motion-control.json)
- [kling-v3-turbo-text-to-video](/docs/en/api-manual/video-series/kling/kling-v3-turbo-text-to-video.json)
- [kling-v3-turbo-image-to-video](/docs/en/api-manual/video-series/kling/kling-v3-turbo-image-to-video.json)
- [kling-o1-image-to-video](/docs/en/api-manual/video-series/kling/kling-o1-image-to-video.json)
- [kling-o1-video-edit](/docs/en/api-manual/video-series/kling/kling-o1-video-edit.json)
- [kling-o1-video-edit-fast](/docs/en/api-manual/video-series/kling/kling-o1-video-edit-fast.json)
- [happyhorse-1.1-text-to-video](/docs/en/api-manual/video-series/happyhorse1.1/happyhorse-1.1-text-to-video.json)
- [happyhorse-1.1-image-to-video](/docs/en/api-manual/video-series/happyhorse1.1/happyhorse-1.1-image-to-video.json)
- [happyhorse-1.1-reference-to-video](/docs/en/api-manual/video-series/happyhorse1.1/happyhorse-1.1-reference-to-video.json)
- [happyhorse-1.0-text-to-video](/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-text-to-video.json)
- [happyhorse-1.0-image-to-video](/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-image-to-video.json)
- [happyhorse-1.0-reference-to-video](/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-reference-to-video.json)
- [happyhorse-1.0-video-edit](/docs/en/api-manual/video-series/happyhorse1.0/happyhorse-1.0-video-edit.json)
- [grok-imagine-video-1.5-preview](/docs/en/api-manual/video-series/grok/grok-imagine-video-1.5-preview.json)
- [grok-imagine-video-1.0-t2v](/docs/en/api-manual/video-series/grok/grok-imagine-video-1.0-t2v.json)
- [grok-imagine-video-1.0-i2v](/docs/en/api-manual/video-series/grok/grok-imagine-video-1.0-i2v.json)
- [grok-imagine-text-to-video](/docs/en/api-manual/video-series/grok/grok-imagine-text-to-video.json)
- [grok-imagine-image-to-video](/docs/en/api-manual/video-series/grok/grok-imagine-image-to-video.json)
- [seedance-1.5-pro-video-generate](/docs/en/api-manual/video-series/seedance1.5/seedance-1.5-pro-video-generate.json)
- [seedance-1.0-pro-fast-video-generate](/docs/en/api-manual/video-series/seedance1.0/seedance-1.0-pro-fast-video-generate.json)
- [sora-2-preview-video-generate](/docs/en/api-manual/video-series/sora2/sora-2-preview-video-generate.json)
- [sora-2-pro-preview-video-generate](/docs/en/api-manual/video-series/sora2pro/sora-2-pro-preview-video-generate.json)
- [veo-3.1-generate-preview-generate](/docs/en/api-manual/video-series/veo3.1/veo-3.1-generate-preview-generate.json)
- [veo3.1-pro-video-generate](/docs/en/api-manual/video-series/veo3.1/veo3.1-pro-video-generate.json)
- [veo-3.1-fast-generate-preview-generate](/docs/en/api-manual/video-series/veo3.1/veo-3.1-fast-generate-preview-generate.json)
- [veo3.1-fast-video-generate](/docs/en/api-manual/video-series/veo3.1/veo3.1-fast-video-generate.json)
- [hailuo-02-video-generate](/docs/en/api-manual/video-series/hailuo/hailuo-02-video-generate.json)
- [hailuo-2-3-video-generate](/docs/en/api-manual/video-series/hailuo/hailuo-2-3-video-generate.json)
- [hailuo-2-3-fast-video-generate](/docs/en/api-manual/video-series/hailuo/hailuo-2-3-fast-video-generate.json)
- [wan3.0-overview](/docs/en/api-manual/video-series/wan3.0/wan3.0-overview.json)
- [wan3.0-text-to-video](/docs/en/api-manual/video-series/wan3.0/wan3.0-text-to-video.json)
- [wan3.0-image-to-video](/docs/en/api-manual/video-series/wan3.0/wan3.0-image-to-video.json)
- [wan3.0-reference-video](/docs/en/api-manual/video-series/wan3.0/wan3.0-reference-video.json)
- [wan3.0-prime-text-to-video](/docs/en/api-manual/video-series/wan3.0/wan3.0-prime-text-to-video.json)
- [wan3.0-prime-image-to-video](/docs/en/api-manual/video-series/wan3.0/wan3.0-prime-image-to-video.json)
- [wan3.0-prime-reference-video](/docs/en/api-manual/video-series/wan3.0/wan3.0-prime-reference-video.json)
- [wan2.7-text-to-video](/docs/en/api-manual/video-series/wan2.7/wan2.7-text-to-video.json)
- [wan2.7-image-to-video](/docs/en/api-manual/video-series/wan2.7/wan2.7-image-to-video.json)
- [wan2.7-reference-video](/docs/en/api-manual/video-series/wan2.7/wan2.7-reference-video.json)
- [wan2.7-video-edit](/docs/en/api-manual/video-series/wan2.7/wan2.7-video-edit.json)
- [wan2.6-text-to-video](/docs/en/api-manual/video-series/wan2.6/wan2.6-text-to-video.json)
- [wan2.6-image-to-video](/docs/en/api-manual/video-series/wan2.6/wan2.6-image-to-video.json)
- [wan2.6-image-to-video-flash](/docs/en/api-manual/video-series/wan2.6/wan2.6-image-to-video-flash.json)
- [wan2.6-reference-video](/docs/en/api-manual/video-series/wan2.6/wan2.6-reference-video.json)
- [wan2.6-reference-video-flash](/docs/en/api-manual/video-series/wan2.6/wan2.6-reference-video-flash.json)
- [wan2.5-text-to-video](/docs/en/api-manual/video-series/wan2.5/wan2.5-text-to-video.json)
- [wan2.5-image-to-video](/docs/en/api-manual/video-series/wan2.5/wan2.5-image-to-video.json)
- [omnihuman-1.5-video-generate](/docs/en/api-manual/video-series/omnihuman/omnihuman-1.5-video-generate.json)
- [videoretalk-video-generate](/docs/en/api-manual/video-series/videoretalk/videoretalk-video-generate.json)
- [topaz-video-upscale](/docs/en/api-manual/video-series/topaz/topaz-video-upscale.json)
- [doubao-seed-audio-1-0](/docs/en/api-manual/audio-series/doubao-seed-audio/doubao-seed-audio-1-0.json)
- [suno-music-generation](/docs/en/api-manual/audio-series/suno/suno-music-generation.json)
- [suno-persona-creation](/docs/en/api-manual/audio-series/suno/suno-persona-creation.json)
- [qwen-voice-design](/docs/en/api-manual/audio-series/qwen-tts/qwen-voice-design.json)
- [qwen3-tts-vd](/docs/en/api-manual/audio-series/qwen-tts/qwen3-tts-vd.json)
- [evolink-auto-quickstart](/docs/en/api-manual/language-series/evolink-auto/evolink-auto-quickstart.json)
- [evolink-auto-claude](/docs/en/api-manual/language-series/evolink-auto/evolink-auto-claude.json)
- [evolink-auto-gemini](/docs/en/api-manual/language-series/evolink-auto/evolink-auto-gemini.json)
- [evolink-moderation-1.0-api](/docs/en/api-manual/language-series/evolink-moderation-1.0/evolink-moderation-1.0-api.json)
- [kimi-k3-chat](/docs/en/api-manual/language-series/kimi-k3/kimi-k3-chat.json)
- [kimi-k3-messages](/docs/en/api-manual/language-series/kimi-k3/kimi-k3-messages.json)
- [claude-messages-api](/docs/en/api-manual/language-series/claude/claude-messages-api.json)
- [native-api-quickstart](/docs/en/api-manual/language-series/gemini/native-api/native-api-quickstart.json)
- [native-api-reference](/docs/en/api-manual/language-series/gemini/native-api/native-api-reference.json)
- [openai-sdk-quickstart](/docs/en/api-manual/language-series/gemini/openai-sdk/openai-sdk-quickstart.json)
- [openai-sdk-reference](/docs/en/api-manual/language-series/gemini/openai-sdk/openai-sdk-reference.json)
- [chat-completions-quickstart](/docs/en/api-manual/language-series/gpt/chat-completions/chat-completions-quickstart.json)
- [chat-completions-reference](/docs/en/api-manual/language-series/gpt/chat-completions/chat-completions-reference.json)
- [responses-quickstart](/docs/en/api-manual/language-series/gpt/responses/responses-quickstart.json)
- [responses-reference](/docs/en/api-manual/language-series/gpt/responses/responses-reference.json)
- [chat-completions-quickstart](/docs/en/api-manual/language-series/grok/chat-completions/chat-completions-quickstart.json)
- [chat-completions-reference](/docs/en/api-manual/language-series/grok/chat-completions/chat-completions-reference.json)
- [responses-quickstart](/docs/en/api-manual/language-series/grok/responses/responses-quickstart.json)
- [responses-reference](/docs/en/api-manual/language-series/grok/responses/responses-reference.json)
- [doubao-seed-2.0-quickstart](/docs/en/api-manual/language-series/doubao-seed-2.0/doubao-seed-2.0-quickstart.json)
- [doubao-seed-2.0-reference](/docs/en/api-manual/language-series/doubao-seed-2.0/doubao-seed-2.0-reference.json)
- [doubao-seed-2.0-responses-quickstart](/docs/en/api-manual/language-series/doubao-seed-2.0/doubao-seed-2.0-responses-quickstart.json)
- [doubao-seed-2.0-responses-reference](/docs/en/api-manual/language-series/doubao-seed-2.0/doubao-seed-2.0-responses-reference.json)
- [deepseek-v4-chat](/docs/en/api-manual/language-series/deepseek-v4/deepseek-v4-chat.json)
- [deepseek-v4-messages](/docs/en/api-manual/language-series/deepseek-v4/deepseek-v4-messages.json)
- [deepseek-v4-responses](/docs/en/api-manual/language-series/deepseek-v4/deepseek-v4-responses.json)
- [deepseek-reference](/docs/en/api-manual/language-series/deepseek/deepseek-reference.json)
- [minimax-m3-chat](/docs/en/api-manual/language-series/minimax-m3/minimax-m3-chat.json)
- [minimax-m3-messages](/docs/en/api-manual/language-series/minimax-m3/minimax-m3-messages.json)
- [minimax-m2.5-api](/docs/en/api-manual/language-series/minimax-m2.5/minimax-m2.5-api.json)
- [qwen3.8-max-chat](/docs/en/api-manual/language-series/qwen3.8-max/qwen3.8-max-chat.json)
- [qwen3.8-max-responses](/docs/en/api-manual/language-series/qwen3.8-max/qwen3.8-max-responses.json)
- [qwen3.8-max-messages](/docs/en/api-manual/language-series/qwen3.8-max/qwen3.8-max-messages.json)
- [chat-completions-quickstart](/docs/en/api-manual/language-series/glm/chat-completions/chat-completions-quickstart.json)
- [chat-completions-reference](/docs/en/api-manual/language-series/glm/chat-completions/chat-completions-reference.json)
- [messages-quickstart](/docs/en/api-manual/language-series/glm/messages/messages-quickstart.json)
- [messages-reference](/docs/en/api-manual/language-series/glm/messages/messages-reference.json)
- [get-credits](/docs/en/api-manual/account-management/get-credits.json)
- [get-task-detail](/docs/en/api-manual/task-management/get-task-detail.json)
- [upload-base64](/docs/en/api-manual/file-series/upload-base64.json)
- [upload-stream](/docs/en/api-manual/file-series/upload-stream.json)
- [upload-url](/docs/en/api-manual/file-series/upload-url.json)
- [quota](/docs/en/api-manual/file-series/quota.json)