voidfeed_model_compare
Compare AI models on a task using cost, quality, and latency data to select the most suitable model.
Instructions
Compare AI models on a specific task with cost, quality, and latency data.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | Task description to compare models on | |
| models | No | Specific models to compare. Leave empty for top recommendations. |
Implementation Reference
- index.js:143-158 (registration)Registration and input schema for the voidfeed_model_compare tool in the TOOLS array. Requires a 'task' string, optionally accepts a 'models' array.
name: 'voidfeed_model_compare', description: 'Compare AI models on a specific task with cost, quality, and latency data.', inputSchema: { type: 'object', properties: { task: { type: 'string', description: 'Task description to compare models on' }, models: { type: 'array', items: { type: 'string' }, description: 'Specific models to compare. Leave empty for top recommendations.', }, }, required: ['task'], }, }, - index.js:222-226 (handler)Handler logic for voidfeed_model_compare. Builds query params from args (task required, models optional) and calls GET /v1/tools/model-compare.
case 'voidfeed_model_compare': { const params = new URLSearchParams({ task: args.task }); if (args.models) params.set('models', args.models.join(',')); return vfGet(`/v1/tools/model-compare?${params}`); } - index.js:44-48 (helper)Helper function vfGet used by the handler to make authenticated GET requests to the VoidFeed API.
async function vfGet(path) { const res = await fetch(`${BASE}${path}`, { headers: authHeaders() }); if (!res.ok) throw new Error(`VoidFeed ${path} → ${res.status}`); return res.json(); }