Media APIs

AnyInt publishes media-generation routes through DashScope and Transtreams Kling. These are not chat-completion endpoints. They have their own request bodies, and Kling and video generation routes are task-based.

Published routes

Route	Purpose
`POST /dashscope/v1/services/aigc/multimodal-generation/generation`	Prompt-driven image generation
`POST /dashscope/v1/services/aigc/video-generation/video-synthesis`	Prompt, image, and audio to video
`GET /dashscope/v1/tasks/{task_id}`	Query video task status and result
`POST /transtreams/kling/v1/images/generations`	Create a Kling v2.1 image task
`GET /transtreams/kling/v1/images/generations/{task_id}`	Query a Kling v2.1 image task
`POST /transtreams/kling/v1/images/omni-image`	Create a Kling V3 Omni image task
`GET /transtreams/kling/v1/images/omni-image/{task_id}`	Query a Kling V3 Omni image task
`POST /transtreams/kling/v1/videos/omni-video`	Create a Kling V3 Omni video task
`GET /transtreams/kling/v1/videos/omni-video/{task_id}`	Query a Kling V3 Omni video task

Authentication

Authorization: Bearer <ANYINT_API_KEY>

Transtreams Kling routes

Use kling-v2-1 for the image model displayed as Kling: Image v2.1. Use kling-v3-omni for Omni image and video tasks; the video model is displayed as Kling: Video v3.0 Omni.

For exact Kling image examples, see Image Generation. For exact Kling video examples and polling behavior, see Kling video.

DashScope image generation

Core request shape

Field	Type	Required	Meaning	Example
`model`	string	Yes	Image-capable model ID available to your account.	`qwen-image-plus`
`input.messages`	array	Yes	Prompt messages for the image request.	`[{"role":"user","content":[...]}]`
`input.messages[].role`	string	Yes	Message role. Use `user` for prompts.	`user`
`input.messages[].content`	array	Yes	Content blocks for prompt text and optional reference media.	`[{"text":"A poster..."}]`
`content[].text`	string	Usually	Text prompt describing the desired image.	`A cinematic product poster...`
`content[].image`	string	Optional	Public HTTPS image URL or supported image input used as reference, when the selected model supports image input.	`https://your-domain.com/ref.png`
`parameters.size`	string	Recommended	Output image size. Supported values depend on the selected model.	`1328*1328`
`parameters.negative_prompt`	string	Optional	Things the model should avoid generating.	`low quality, blurry`
`parameters.prompt_extend`	boolean	Optional	Whether the provider may expand or rewrite the prompt.	`true`
`parameters.watermark`	boolean	Optional	Whether to include a provider watermark when supported.	`false`

cURL example

Replace the media URLs with publicly reachable HTTPS assets from your own storage.

curl https://gateway.api.anyint.ai/dashscope/v1/services/aigc/multimodal-generation/generation \
  -H "Authorization: Bearer $ANYINT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-plus",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": [
            {
              "text": "A cinematic product poster for an AI music launch, neon highlights, premium studio lighting."
            }
          ]
        }
      ]
    },
    "parameters": {
      "negative_prompt": "",
      "prompt_extend": true,
      "watermark": false,
      "size": "1328*1328"
    }
  }'

Useful response fields:

Field	Meaning
`output.choices[0].message.content[].image`	Generated image URL or image payload returned by the provider
`usage.width`	Output width when returned
`usage.height`	Output height when returned
`usage.image_count`	Number of generated images when returned

DashScope video generation

Core request shape

Field	Type	Required	Meaning	Example
`model`	string	Yes	Video-capable model ID available to your account.	`wan2.5-i2v-preview`
`input.prompt`	string	Yes	Text description of the video to generate.	`A neon street scene with slow camera movement.`
`input.img_url`	string	Optional	Public HTTPS source image URL for image-to-video flows.	`https://your-domain.com/source-image.png`
`input.audio_url`	string	Optional	Public HTTPS audio URL when the selected model supports audio-guided video.	`https://your-domain.com/source-audio.mp3`
`parameters.resolution`	string	Optional	Output resolution. Supported values depend on the selected model.	`720P`
`parameters.duration`	integer	Optional	Target duration in seconds.	`10`
`parameters.audio`	boolean	Optional	Whether to include or use audio when supported.	`true`
`parameters.shot_type`	string	Optional	Camera or shot behavior when supported.	`multi`
`parameters.prompt_extend`	boolean	Optional	Whether the provider may expand or rewrite the prompt.	`true`

cURL example

curl https://gateway.api.anyint.ai/dashscope/v1/services/aigc/video-generation/video-synthesis \
  -H "Authorization: Bearer $ANYINT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.5-i2v-preview",
    "input": {
      "prompt": "A graffiti rapper comes to life under a railway bridge at night and performs to the beat.",
      "img_url": "https://your-domain.com/source-image.png",
      "audio_url": "https://your-domain.com/source-audio.mp3"
    },
    "parameters": {
      "resolution": "720P",
      "prompt_extend": true,
      "duration": 10,
      "audio": true,
      "shot_type": "multi"
    }
  }'

Response pattern

This is a task-based API. The response returns:

Field	Meaning
`request_id`	Request tracing identifier when returned
`output.task_id`	Task ID to store and use for polling
`output.task_status`	Initial task state, commonly `PENDING`
`metadata.provider`	Provider metadata when returned

Video task query

The current catalog shows a task query path in the form:

GET /dashscope/v1/tasks/{task_id}

Apifox currently includes one sample task ID directly in the example path. Treat that as a path template rather than a fixed ID.

Query example

curl https://gateway.api.anyint.ai/dashscope/v1/tasks/your-task-id \
  -H "Authorization: Bearer $ANYINT_API_KEY"

Query response fields

Field	Meaning
`output.task_status`	Current task state
`output.video_url`	Generated video URL after success
`output.actual_prompt`	Prompt used after provider-side expansion
`usage.duration`	Generated duration
`usage.video_count`	Number of outputs

In the published examples, video tasks move from PENDING to SUCCEEDED.

HappyHorse video generation

HappyHorse is available through the DashScope-compatible video synthesis API. Create a video task first, then poll the task endpoint until output.task_status becomes SUCCEEDED. Use happyhorse-1.0-t2v as the model. The request can include a prompt, a source image URL, and a source audio URL. The initial response returns request_id for tracing and output.task_id for result polling.

Create a video task

Replace the media URLs with publicly reachable HTTPS assets from your own storage.

curl --location --request POST 'https://gateway.api.anyint.ai/dashscope/v1/services/aigc/video-generation/video-synthesis' \
  --header "Authorization: Bearer $ANYINT_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "model": "happyhorse-1.0-t2v",
    "input": {
      "prompt": "An urban fantasy scene in cinematic style. A graffiti-painted teenage rapper comes alive from a concrete wall under a railway bridge at night, performs a fast English rap, and strikes an energetic classic rapper pose. The only audio is the rap, with no extra dialogue or noise.",
      "img_url": "https://your-domain.com/source-image.png",
      "audio_url": "https://your-domain.com/source-audio.mp3"
    },
    "parameters": {
      "resolution": "720P",
      "prompt_extend": true,
      "duration": 10,
      "audio": true,
      "shot_type": "multi"
    }
  }'

Response example:

{
  "request_id": "570dd72c-52ae-9151-b819-411edf66069e",
  "output": {
    "task_id": "c25723f0-8f2b-401a-b843-7ae05ae4e5e3",
    "task_status": "PENDING"
  }
}

Query the generated video

Use the output.task_id from the previous response:

curl --location --request GET "https://gateway.api.anyint.ai/dashscope/v1/tasks/$TASK_ID" \
  --header "Authorization: Bearer $ANYINT_API_KEY"

Response example:

{
  "request_id": "1e1fb115-c22a-9769-af2c-056451a8f692",
  "output": {
    "task_id": "a54b0585-aa49-45be-8786-fc46414634da",
    "task_status": "SUCCEEDED",
    "submit_time": "2026-04-27 17:01:39.657",
    "scheduled_time": "2026-04-27 17:01:39.689",
    "end_time": "2026-04-27 17:07:10.758",
    "orig_prompt": "An urban fantasy scene in cinematic style...",
    "video_url": "https://example.com/generated-video.mp4"
  },
  "usage": {
    "duration": 10,
    "input_video_duration": 0,
    "output_video_duration": 10,
    "video_count": 1,
    "SR": 720,
    "ratio": "16:9"
  }
}

Copy output.video_url into a browser to preview or download the generated video. Video URLs are temporary, so save the file if you need to keep it.

When to use media APIs vs AI Music

Use media APIs for:

image generation
prompt-to-video
image-plus-audio-to-video

Use AI Music for:

song generation
cover workflows
personas
lyrics
stems
music video generation tied to Suno tasks

Common mistakes

Treating the example task ID in Apifox as a fixed route
Assuming video generation returns the final MP4 in the initial response
Reusing Gemini image-generation payloads against DashScope routes

On this page