& View-2.0-gl series

seedance-2.0-gl is a MoonNexAI Seedance-2 mixed-reference video family. Standard, Fast and Mini use /v1/videos for task creation and queries.

Model Selection

Models	Positioning	resolution	billing Method
`seedance-2.0-gl`	Standard mixed-reference generation	`480P`, `720P`, `1080P`	Billed by output tokens
`seedance-2.0-gl-fast`	Fast mixed-reference generation	`480P`, `720P`	Billed by output tokens
`seedance-2.0-gl-mini`	Lightweight mixed-reference generation	`480P`, `720P`	Billed by output tokens

Check the model-list API and MoonNexAI console for prices, available groups and current capabilities. Documentation does not fix monetary amounts.

Capacity boundaries

Capacity	Support
text-to-video	Support
Picture reference	Up to 9
Video reference	Up to 3
Audio Reference	Up to 3; cannot be submitted separately, need to be accompanied by pictures or videos
Mixed media assets	Up to 15 references media assets
duration	`4` to `15` seconds
aspect ratio	`16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `21:9`, `adaptive`, based on model capabilities
Realist reference.	Support; media assets still requires content security clearance

first frame, last frame, and reference images, regular, belong to the scale of media assets. When the specific model does not support a aspect ratio or field, the model list capacity is used; do not apply the 1080P capability of the standard version to Fast or Mini.

Subbar for request Parameters

MoonNexAI Unified Universal Video Parameters

The unified access is POST /v1/videos, and prompt, references[], aspect_ratio and size are recommended.

field	Type	Annotations
`model`	string	`seedance-2.0-gl`, `seedance-2.0-gl-fast` or `seedance-2.0-gl-mini`.
`prompt`	string	Video description, with `@alias` references to media assets.
`references[]`	array	General image, video and audio media assets arrays.
`duration`	number	`4` to `15` seconds.
`aspect_ratio`	string	Video aspect ratio.
`size`	string	Output size, completed by model capability.
`generate_audio`	boolean	Whether or not to generate audio.

Volcengine-compatible compatible parameters

Compatible access is POST /api/v3/contents/generations/tasks, using official content[], ratio and resolution; do not submit references[] and content[] simultaneously in one request.

field	Type	Annotations
`model`	string	Still fills out the name of the MoonNexAI public model for the GL series.
`content[]`	array	Official text, pictures, videos and audio entries.
`duration`	number	Compatible duration field.
`ratio`	string	Compatible aspect-ratio field.
`resolution`	string	Compatible resolution field.
`generate_audio`	boolean	Official audio generation switch.
`watermark`	boolean	Official watermark switch.
`seed`	integer	Official random seeds.
`callback_url`	string	Official callback address.

Create task

bash

curl https://moonnexai.com/v1/videos \
  -H "Authorization: Bearer <MOONNEXAI_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0-gl-mini",
    "prompt": "保持参考素材中的主体特征一致，生成自然的镜头运动。",
    "duration": 4,
    "aspect_ratio": "16:9",
    "size": "720P",
    "references": [
      {
        "media_type": "image",
        "role": "reference_image",
        "url": "https://example.com/subject.png",
        "alias": "主体"
      },
      {
        "media_type": "video",
        "role": "reference_video",
        "url": "https://example.com/motion.mp4",
        "alias": "动作"
      },
      {
        "media_type": "audio",
        "role": "reference_audio",
        "url": "https://example.com/music.mp3",
        "alias": "音乐"
      }
    ]
  }'

Basic example (Volcengine-compatible compatible parameters)

bash

curl https://moonnexai.com/api/v3/contents/generations/tasks \
  -H "Authorization: Bearer <MOONNEXAI_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0-gl-mini",
    "content": [
      { "type": "text", "text": "保持参考素材中的主体特征一致，生成自然的镜头运动。" },
      { "type": "image_url", "role": "reference_image", "image_url": { "url": "https://example.com/subject.png" }, "alias": "主体" }
    ],
    "duration": 4,
    "ratio": "16:9",
    "resolution": "720P"
  }'

The model option is to select other public models by changing seedance-2.0-gl or seedance-2.0-gl-fast. The client 's own stable HTTPS public network URL priority; if media assets is needed, you can first create the current model 's Asset://asset_xxx 's available by /v1/assets/uploads and then insert the reference into references[].url.

Multigraph + MultiVideo + Multi Audio (MoonNexAI Unified Generic Parameters)

The GL series supports a hybrid reference to media assets. The following example is used with 2 pictures, 2 videos and 2 segments of audio; audio cannot be submitted separately from a picture or video, the actual number still being based on the current model.

json

{
  "model": "seedance-2.0-gl",
  "prompt": "保持 @hero1 和 @hero2 的外观一致，参考 @motion1、@motion2 的镜头节奏，并融合 @music1、@music2 的声音氛围。",
  "duration": 8,
  "aspect_ratio": "16:9",
  "resolution": "720P",
  "generate_audio": true,
  "references": [
    { "media_type": "image", "role": "reference_image", "url": "https://example.com/hero-1.png", "alias": "hero1" },
    { "media_type": "image", "role": "reference_image", "url": "https://example.com/hero-2.png", "alias": "hero2" },
    { "media_type": "video", "role": "reference_video", "url": "https://example.com/motion-1.mp4", "alias": "motion1" },
    { "media_type": "video", "role": "reference_video", "url": "https://example.com/motion-2.mp4", "alias": "motion2" },
    { "media_type": "audio", "role": "reference_audio", "url": "https://example.com/music-1.mp3", "alias": "music1" },
    { "media_type": "audio", "role": "reference_audio", "url": "https://example.com/music-2.mp3", "alias": "music2" }
  ]
}

URLs must be stable public media addresses accessible anonymously by the server. For Fast/Mini, replace model with the corresponding public ID and check that it supports the selected resolution.

Multigraph + MultiVideo + Multi Audio (Volcengine-compatible compatible parameters)

json

{
  "model": "seedance-2.0-gl",
  "content": [
    { "type": "text", "text": "保持 @hero1 和 @hero2 的外观一致，参考 @motion1、@motion2 的镜头节奏，并融合 @music1、@music2 的声音氛围。" },
    { "type": "image_url", "role": "reference_image", "image_url": { "url": "https://example.com/hero-1.png" }, "alias": "hero1" },
    { "type": "image_url", "role": "reference_image", "image_url": { "url": "https://example.com/hero-2.png" }, "alias": "hero2" },
    { "type": "video_url", "role": "reference_video", "video_url": { "url": "https://example.com/motion-1.mp4" }, "alias": "motion1" },
    { "type": "video_url", "role": "reference_video", "video_url": { "url": "https://example.com/motion-2.mp4" }, "alias": "motion2" },
    { "type": "audio_url", "role": "reference_audio", "audio_url": { "url": "https://example.com/music-1.mp3" }, "alias": "music1" },
    { "type": "audio_url", "role": "reference_audio", "audio_url": { "url": "https://example.com/music-2.mp3" }, "alias": "music2" }
  ],
  "duration": 8,
  "ratio": "16:9",
  "resolution": "720P",
  "generate_audio": true
}

List of Parameters

MoonNexAI Unified Universal field

field	Type	Annotations
`model`	string	`seedance-2.0-gl`, `seedance-2.0-gl-fast` or `seedance-2.0-gl-mini`.
`prompt`	string	Video description and reference bindings. `@alias` in the prompt corresponds to `references[].alias`.
`duration`	integer	`4` to `15` seconds.
`size`	string	Target resolution. Standard version can be used for `480P`, `720P`, `1080P`; Fast/Mini is based on the ability to return to the model list.
`aspect_ratio`	string	Target aspect ratio, which is based on the range of support for the selected model.
`references`	array	Recommended unified media assets array; maximum 9 pictures, maximum 3 videos and maximum 3 audio, total 15.
`references[].media_type`	string	`image`, `video`, `audio` or `music`.
`references[].role`	string	`reference_image`, `first_frame`, `last_frame`, `reference_video`, `reference_audio`.
`references[].url`	string	Client stabilizes the public network URL, or `Asset://asset_xxx` is currently ready for the current model.
`references[].alias`	string	Select an alias without `@`; in `prompt` use `@alias` as the name.
`generate_audio`	boolean	Optional, controls whether or not to generate audio tracks; the specific default behaviour is based on the model list capability.

Volcengine-compatible compatible field

field	Type	Annotations
`content[]`	array	Official multi-modular input arrays.
`ratio`	string	Compatible aspect-ratio field.
`resolution`	string	Compatible resolution field.
`duration`	number	Compatible duration field.
`generate_audio`	boolean	Official audio generation switch.
`watermark`	boolean	Official watermark switch.
`seed`	integer	Official random seeds.
`callback_url`	string	Official callback address.

media assets ready.

When sending URLs directly, the address should allow anonymous downloads, without relying on login, Cookie or additional authentication Header, and keep the real file suffix.
Use /v1/assets/uploads mode=asset when a long-term reuse or model media assets ID is required and enter the target model name; wait for media assets to be ready and generation_ready=true to be generated.
Multipart uploads the MoonNexAI hosting URL as a select transfer only, and the official business gives priority to the customer's own SURL.
media assets references for different model lines are not mixed; the availability of Asset://asset_xxx depends on the model and media assets status specified at the time of creation.
Truth media assets is still subject to content security clearance; “support for truth references” does not mean that any real person or sensitive content is a guarantee of success.

Query and Results

Create response to only task has been submitted. Save id or task_id, and re-examine:

bash

curl https://moonnexai.com/v1/videos/{task_id} \
  -H "Authorization: Bearer <MOONNEXAI_API_KEY>"

Check status and error, only if task is successful and read the results. You can also download with the standard content entry:

bash

curl -L https://moonnexai.com/v1/videos/{task_id}/content \
  -H "Authorization: Bearer <MOONNEXAI_API_KEY>" \
  -o output.mp4

Conversation APIs

Embeddings

Audio

Models

GPT Image

Gemini Nano

Ideogram Image

Midjourney Task

Seedance-2 Video

Moon-2 Video

& View-2.0-gl series

Model Selection

Capacity boundaries

Subbar for request Parameters

MoonNexAI Unified Universal Video Parameters

Volcengine-compatible compatible parameters

Create task

Basic example (Volcengine-compatible compatible parameters)

Multigraph + MultiVideo + Multi Audio (MoonNexAI Unified Generic Parameters)

Multigraph + MultiVideo + Multi Audio (Volcengine-compatible compatible parameters)

List of Parameters

MoonNexAI Unified Universal field

Volcengine-compatible compatible field

media assets ready.

Query and Results

Relevant Pages

Ideogram Image

Midjourney Task

Seedance-2 Video

Moon-2 Video

& View-2.0-gl series ​

Model Selection ​

Capacity boundaries ​

Subbar for request Parameters ​

MoonNexAI Unified Universal Video Parameters ​

Volcengine-compatible compatible parameters ​

Create task ​

Basic example (Volcengine-compatible compatible parameters) ​

Multigraph + MultiVideo + Multi Audio (MoonNexAI Unified Generic Parameters) ​

Multigraph + MultiVideo + Multi Audio (Volcengine-compatible compatible parameters) ​

List of Parameters ​

MoonNexAI Unified Universal field ​

Volcengine-compatible compatible field ​

media assets ready. ​

Query and Results ​

Relevant Pages ​

& View-2.0-gl series

Model Selection

Capacity boundaries

Subbar for request Parameters

MoonNexAI Unified Universal Video Parameters

Volcengine-compatible compatible parameters

Create task

Basic example (Volcengine-compatible compatible parameters)

Multigraph + MultiVideo + Multi Audio (MoonNexAI Unified Generic Parameters)

Multigraph + MultiVideo + Multi Audio (Volcengine-compatible compatible parameters)

List of Parameters

MoonNexAI Unified Universal field

Volcengine-compatible compatible field

media assets ready.

Query and Results

Relevant Pages