analyze_video
Analyze a video by asking questions about its content. Provide a public URL or local file path, and get detailed answers from an AI that natively reads the footage.
Instructions
Watch and analyze a video using Qwen3.8-Max (native multimodal). Use this whenever you need to see a video you cannot view natively. The model reads the video natively — no client-side frame extraction. Pass a public URL (http/https) or a local file path; local files are sent inline as a base64 data URL (25MB guardrail).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"video_url": "<video_url>"
},
"name": "analyze_video"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| question | No | Question or prompt about the video | Describe what happens in this video in detail. |
| video_url | Yes | Public URL or local file path of the video to analyze | |
| max_tokens | No | Maximum tokens in the response | |
| thinking_budget | No | Maximum tokens the model may spend on thinking before answering (Qwen hybrid-thinking models). Omit to use the provider default. |