bittensor_multimodal
Analyze images with text prompts using Bittensor's multimodal AI to extract insights and answer questions about visual content.
Instructions
Image + text reasoning via Bittensor subnet 24 (Omega Multimodal). Cost: $0.02 per call.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Text prompt or question about the image | |
| image_url | No | URL of the image to analyse |
Implementation Reference
- src/index.ts:291-297 (handler)Handler implementation for the "bittensor_multimodal" tool, which sends a request to the gateway with a prompt and an optional image_url.
case "bittensor_multimodal": result = await callGateway({ route: "bittensor-multimodal", prompt: a.prompt, ...(a.image_url ? { image_url: a.image_url } : {}), }); break; - src/index.ts:186-197 (schema)Tool registration schema for "bittensor_multimodal".
name: "bittensor_multimodal", description: "Image + text reasoning via Bittensor subnet 24 (Omega Multimodal). Cost: $0.02 per call.", inputSchema: { type: "object", properties: { prompt: { type: "string", description: "Text prompt or question about the image" }, image_url: { type: "string", description: "URL of the image to analyse" }, }, required: ["prompt"], }, },