Skip to content

Moon-2.0-me series ​

moon-2.0-me is the 720P of MoonNexAI, which supports text-to-video, image-to-video and reference media assets video by sub-video model series. Please use open model names in request and do not depend on the parameters boundaries of other models.

Available Models ​

Open ModelFit to sceneKey competencies
moon-2.0-me-a-720pStandard Picture reference videotext-to-video or up to 9 photo references; reference video and reference audio are not supported.
moon-2.0-me-b-720pMixed-media reference videoText-to-video or up to 9 images, 3 videos and 3 audio files, at most 15 references total.
moon-2.0-me-a-fastFast Picture reference videoThe capacity boundary is the same as A 720P; up to 9 photo references are not supported reference video and reference audio.

All three models support 720P, 5 / 10 / 15 seconds and 16:9, 9:16, 1:1, 4:3, 3:4. Check the model list, pricing page and billing records for availability and prices.

Capacity boundaries ​

CapacityA 720P / A FastB 720P
text-to-videoSupportSupport
Picture referenceUp to 9Up to 9
Video referenceNot supportedUp to 3
Audio ReferenceNot supportedUp to 3
Total reference media assetsMaximum 9Maximum 15
Audio is submitted separatelyNot applicableNot supported; at least one picture or one video at the same time
Output resolution720P720P
duration5, 10, 15 sec5, 10, 15 sec
aspect ratio16:9, 9:16, 1:1, 4:3, 3:416:9, 9:16, 1:1, 4:3, 3:4

Recommendation request ​

Single Picture Reference ​

bash
curl https://moonnexai.com/v1/videos \
  -H "Authorization: Bearer <MOONNEXAI_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moon-2.0-me-a-720p",
    "prompt": "让 @主体 缓慢向镜头走来,保持主体外观和冷色光线,电影感运镜。",
    "duration": 15,
    "ratio": "16:9",
    "resolution": "720P",
    "references": [
      {
        "media_type": "image",
        "role": "reference_image",
        "url": "https://example.com/subject.jpg",
        "alias": "主体"
      }
    ]
  }'

Nine, one video, one audio. ​

json
{
  "model": "moon-2.0-me-b-720p",
  "prompt": "参考图片保持场景和色彩,参考视频提供运动节奏,使用参考音频作为背景声音。",
  "duration": 15,
  "ratio": "16:9",
  "resolution": "720P",
  "references": [
    {
      "media_type": "image",
      "role": "reference_image",
      "url": "https://example.com/image-1.jpg"
    },
    {
      "media_type": "image",
      "role": "reference_image",
      "url": "https://example.com/image-2.jpg"
    },
    {
      "media_type": "video",
      "role": "reference_video",
      "url": "https://example.com/motion.mp4",
      "alias": "运动"
    },
    {
      "media_type": "audio",
      "role": "reference_audio",
      "url": "https://example.com/sound.wav",
      "alias": "声音"
    }
  ]
}

The previous example shows only two pictures; actually up to nine images can be uploaded. Audio must be submitted with a picture or video. alias does not contain @, prompt with @alias as media assets.

Query task ​

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

Check status and error. Only task success will result field be read; standard content entry is also used:

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

Attention ​

  • References must use stable direct public URLs accessible anonymously throughout task execution, without cookies or extra headers.
  • URL suggests that real file suffixes such as .jpg, .png, .mp4, .wav or .mp3 be retained.
  • Use the asset API when reuse is needed. Support for Asset://asset_xxx depends on the target model and asset status.
  • task final duration and result field are based on the return of query API and not on the task success judgement based on request parameters alone.

Relevant Pages ​