Minicpm V Video
Playground
Try it on WaveSpeedAI!MiniCPM-V 4.5 is the latest, most capable MiniCPM-V model for AI video understanding and analysis. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
MiniCPM-V Video is an advanced video understanding model that analyzes video content and generates detailed descriptions, summaries, or answers to your questions. Simply upload a video and let the AI understand what’s happening on screen.
Why It Stands Out
- Video understanding: Analyzes visual content, actions, and scenes in videos.
- Preset prompts: Choose from ready-to-use prompts like “describe” for quick analysis.
- Custom prompts: Ask specific questions or request particular types of analysis.
- Affordable pricing: Get video insights at a low cost per analysis.
- Reproducibility: Use the seed parameter to get consistent results.
Parameters
| Parameter | Required | Description |
|---|---|---|
| video | Yes | Source video (upload or public URL). |
| preset_prompt | No | Pre-defined prompt type (e.g., describe & caption). |
| custom_prompt | No | Your own question or instruction about the video. |
| seed | No | Set for reproducibility; -1 for random. |
| enable_sync_mode | No | Wait for result before returning response (API only). |
How to Use
- Upload your video — drag and drop a file or paste a public URL.
- Select a preset prompt — choose “describe” or other available options for quick analysis.
- Add a custom prompt (optional) — ask specific questions about the video content.
- Click Run and wait for analysis.
- Review the output — get detailed descriptions or answers about your video.
Best Use Cases
- Content Analysis — Understand what’s happening in videos without watching them.
- Video Cataloging — Generate descriptions for video libraries and archives.
- Accessibility — Create text descriptions of video content for accessibility purposes.
- Content Moderation — Analyze video content for review and categorization.
- Research & Analysis — Extract insights from video data at scale.
- Social Media — Generate captions and descriptions for video posts.
Pricing
| Output | Price |
|---|---|
| Per video | $0.015 |
Pro Tips for Best Quality
- Use videos with clear visuals for more accurate analysis.
- Use preset prompts for quick, general descriptions.
- Use custom prompts to ask specific questions like “What objects are in this video?” or “Describe the main action.”
- Keep videos reasonably short for faster processing.
- Fix the seed when you need consistent results across multiple runs.
Notes
- Ensure uploaded video URLs are publicly accessible.
- Processing time varies based on video length and current queue load.
- Please ensure your content complies with usage guidelines.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"preset_prompt": "describe",
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/minicpm-v/video" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}")
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}")
RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
esac
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| video | string | Yes | - | Video to be analyzed. | |
| preset_prompt | string | No | describe | describe, caption | Preset prompt for image analysis. |
| custom_prompt | string | No | - | - | Custom prompt for image analysis. |
| seed | integer | No | -1 | - | The random seed to use for the generation. |
| enable_sync_mode | boolean | No | false | - | If set to `true`, the request attempts to wait for the generated result and return outputs in the same response. If the result is not ready within the sync wait window, the API can return a timeout body while the task continues processing. This option is only available via the API and is supported only by some models. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |