Create Response · Moss API

Request parameters

FieldTypeRequiredDescription

model: stringRequired

Model ID. Use the stable model ID for regular calls, or a snapshot model ID when you need to reproduce results from a fixed version.

input: arrayRequired

The input message array. It must currently contain exactly one message with role=user.

input[].role: stringRequired

Currently fixed to user.

input[].content: arrayRequired

The content array must include at least one non-empty input_text part and either 1–5 input_image parts or 1 input_video part. Images and video cannot be mixed in one request.

input[].content[].type: stringRequired

Content type.

input_text.text: stringRequired

The image or video understanding instruction. It must be a non-empty string.

input_image.image_url: stringConditional

An image URL reachable by the service; mutually exclusive with file_id in the same content item. Each image can be up to 30 MB. Supported formats: PNG, JPG, JPEG, WebP, BMP, GIF, and TIFF.

input_image.file_id: stringConditional

The ID of an uploaded image; mutually exclusive with image_url in the same content item. Each image can be up to 30 MB. Supported formats: PNG, JPG, JPEG, WebP, BMP, GIF, and TIFF.

input_video.video_url: stringConditional

A video URL reachable by the service; mutually exclusive with file_id in the same content item. Each video can be up to 200 MB, with no current duration limit. Supported formats: MP4, M4V, AVI, MOV, WebM, and MKV.

input_video.file_id: stringConditional

The ID of an uploaded video; mutually exclusive with video_url in the same content item. Each video can be up to 200 MB, with no current duration limit. Supported formats: MP4, M4V, AVI, MOV, WebM, and MKV.

max_output_tokens: integerOptional

The maximum number of output tokens, from 1 to 8192.

Return value

The endpoint returns a Responses API object. Model-generated text is available at output[].content[].text; use status to determine whether the output is complete.

FieldTypeDescription

status: string

The response status, currently completed or incomplete.

incomplete_details.reason: string | null

The reason for incomplete output; max_output_tokens when the output limit is reached.

output: array

The output item list.

output[].content: array

The output content list.

output[].content[].type: string

Currently output_text for text results.

output[].content[].text: string

The text generated by the model.

usage.input_tokens: integer

The input tokens used for this request.

usage.output_tokens: integer

The output tokens generated for this request.

usage.total_tokens: integer

The total input and output token count.

The response also contains common metadata such as the ID, object type, timestamps, and model. See the response example on the right for the full structure. Clients should ignore unused additional fields; usage only reports the token usage for this request.

Error codes

HTTP	error.code	Trigger	Suggested action
400	`missing_required_field`	A text instruction or media content is missing	Ensure `input[].content` contains both non-empty `input_text` and valid media.
400	`media_count_exceeded`	More than 5 images or more than 1 video is provided	Keep each request to 1–5 images or 1 video.
400	`mixed_media_not_supported`	Images and video are provided in the same request	Send image understanding and video understanding as separate requests.
400	`invalid_media_source`	A media item has both a URL and `file_id`, or neither	Set only the matching URL field or `file_id` on each media item.
400	`unsupported_media_format`	An uploaded or referenced media format is unsupported	Use a documented media format and keep the file within the size limit.

Next steps

Upload File

Upload an image or video and obtain a reusable file_id.

Request Limits

Review the stable public API input limits.

Request example

curl -X POST "https://api.mosi.cn/v1/responses" \
  -H "Authorization: Bearer $MOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "moss-vl-1.0",
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Describe the main content of this image."
        },
        {
          "type": "input_image",
          "image_url": "https://example.com/image.jpg"
        }
      ]
    }
  ],
  "max_output_tokens": 1024
}'

import os
import requests

response = requests.post(
        "https://api.mosi.cn/v1/responses",
        headers={
        "Authorization": f"Bearer {os.environ['MOSS_API_KEY']}",
        "Content-Type": "application/json",
        },
        json={
            "model": "moss-vl-1.0",
            "input": [
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "input_text",
                            "text": "Describe the main content of this image.",
                        },
                        {
                            "type": "input_image",
                            "image_url": "https://example.com/image.jpg",
                        },
                    ],
                },
            ],
            "max_output_tokens": 1024,
        },
)

response.raise_for_status()
print(response.json())

const response = await fetch("https://api.mosi.cn/v1/responses", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.MOSS_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "moss-vl-1.0",
    "input": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "Describe the main content of this image."
          },
          {
            "type": "input_image",
            "image_url": "https://example.com/image.jpg"
          }
        ]
      }
    ],
    "max_output_tokens": 1024
  }),
})

if (!response.ok) throw new Error(`HTTP ${response.status}`)
console.log(await response.json())

curl -X POST "https://api.mosi.cn/v1/responses" \
  -H "Authorization: Bearer $MOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "moss-vl-1.0",
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Compare the similarities and differences between these images."
        },
        {
          "type": "input_image",
          "file_id": "<image_file_id_1>"
        },
        {
          "type": "input_image",
          "file_id": "<image_file_id_2>"
        }
      ]
    }
  ],
  "max_output_tokens": 1024
}'

import os
import requests

response = requests.post(
        "https://api.mosi.cn/v1/responses",
        headers={
        "Authorization": f"Bearer {os.environ['MOSS_API_KEY']}",
        "Content-Type": "application/json",
        },
        json={
            "model": "moss-vl-1.0",
            "input": [
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "input_text",
                            "text": "Compare the similarities and differences between these images.",
                        },
                        {
                            "type": "input_image",
                            "file_id": "<image_file_id_1>",
                        },
                        {
                            "type": "input_image",
                            "file_id": "<image_file_id_2>",
                        },
                    ],
                },
            ],
            "max_output_tokens": 1024,
        },
)

response.raise_for_status()
print(response.json())

const response = await fetch("https://api.mosi.cn/v1/responses", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.MOSS_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "moss-vl-1.0",
    "input": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "Compare the similarities and differences between these images."
          },
          {
            "type": "input_image",
            "file_id": "<image_file_id_1>"
          },
          {
            "type": "input_image",
            "file_id": "<image_file_id_2>"
          }
        ]
      }
    ],
    "max_output_tokens": 1024
  }),
})

if (!response.ok) throw new Error(`HTTP ${response.status}`)
console.log(await response.json())

curl -X POST "https://api.mosi.cn/v1/responses" \
  -H "Authorization: Bearer $MOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "moss-vl-1.0",
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Summarize the events in this video in chronological order."
        },
        {
          "type": "input_video",
          "video_url": "https://example.com/video.mp4"
        }
      ]
    }
  ],
  "max_output_tokens": 1024
}'

import os
import requests

response = requests.post(
        "https://api.mosi.cn/v1/responses",
        headers={
        "Authorization": f"Bearer {os.environ['MOSS_API_KEY']}",
        "Content-Type": "application/json",
        },
        json={
            "model": "moss-vl-1.0",
            "input": [
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "input_text",
                            "text": "Summarize the events in this video in chronological order.",
                        },
                        {
                            "type": "input_video",
                            "video_url": "https://example.com/video.mp4",
                        },
                    ],
                },
            ],
            "max_output_tokens": 1024,
        },
)

response.raise_for_status()
print(response.json())

const response = await fetch("https://api.mosi.cn/v1/responses", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.MOSS_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "moss-vl-1.0",
    "input": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "Summarize the events in this video in chronological order."
          },
          {
            "type": "input_video",
            "video_url": "https://example.com/video.mp4"
          }
        ]
      }
    ],
    "max_output_tokens": 1024
  }),
})

if (!response.ok) throw new Error(`HTTP ${response.status}`)
console.log(await response.json())

Response example

{
  "id": "resp_task_abc123",
  "object": "response",
  "created_at": 1710000000,
  "status": "completed",
  "completed_at": 1710000001,
  "error": null,
  "incomplete_details": null,
  "model": "moss-vl-1.0",
  "output": [
    {
      "id": "msg_task_abc123",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "There are four nuts in the image."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 8743,
    "output_tokens": 94,
    "total_tokens": 8837
  }
}