Molmo2-4B Video Understanding: Analyze videos with specialized tasks (general, summary, analysis, counting, scene description). Open-source vision-language model with temporal understanding. Ready-to-use REST API, no cold starts, duration-based pricing.
Idle
$0.005per run·~200 / $1
Analyze and understand video content with Molmo2 Video Understanding. This intelligent video analysis model performs various tasks including summarization, scene description, object counting, and detailed analysis — perfect for video cataloging, content moderation, and automated video workflows.
| Parameter | Required | Description |
|---|---|---|
| video | Yes | Video to analyze (upload or public URL). |
| task | No | Analysis type: general, summary, analysis, counting, or scene_description. Default: general. |
| text | No | Additional instructions or focus areas for the analysis. |
Per 5-second billing with minimum charge for videos ≤5 seconds. Maximum billable duration is 120 seconds.
| Duration | Cost |
|---|---|
| ≤5 seconds | $0.005 |
| 10 seconds | $0.01 |
| 30 seconds | $0.03 |
| 60 seconds | $0.06 |
| 120 seconds (max) | $0.12 |
| Task | Description | Best For |
|---|---|---|
| general | Open-ended video understanding and Q&A | Custom questions, flexible analysis |
| summary | Concise overview of video content | Quick content review, cataloging |
| analysis | Detailed breakdown of video elements | In-depth understanding, reports |
| counting | Count objects, people, or events | Inventory, crowd analysis, metrics |
| scene_description | Describe scenes and visual elements | Accessibility, content tagging |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/molmo2/video-understanding with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Molmo2 Video Understanding below.
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/molmo2/video-understanding" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"video": "https://example.com/your-input.mp4",
"task": "general"
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("wavespeed-ai/molmo2/video-understanding", {
"video": "https://example.com/your-input.mp4",
"task": "general"
});
console.log(result.outputs[0]); // → URL of the generated output# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/molmo2/video-understanding",
{
"video": "https://example.com/your-input.mp4",
"task": "general"
}
)
print(output["outputs"][0]) # → URL of the generated outputMolmo2 Video Understanding is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. Molmo2-4B Video Understanding: Analyze videos with specialized tasks (general, summary, analysis, counting, scene description). Open-source vision-language model with temporal understanding. Ready-to-use REST API, no cold starts, duration-based pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/molmo2-video-understanding.
Molmo2 Video Understanding starts at $0.005 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `video`, `task`, `text`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/molmo2-video-understanding.
Average end-to-end generation time on WaveSpeedAI is around 16 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.