batch_create
Create async batch content generation jobs with Gemini AI at reduced cost. Upload JSONL files or use inline requests to process large-scale content tasks with ~24-hour turnaround.
Instructions
CREATE BATCH JOB - Create async content generation batch job with Gemini. COST: 50% cheaper than standard API. TURNAROUND: ~24 hours target. WORKFLOW: 1) Prepare JSONL file with requests (or use batch_ingest_content first), 2) Upload file with upload_file, 3) Call batch_create with file URI, 4) Use batch_get_status to monitor progress, 5) Use batch_download_results when complete. SUPPORTS: Inline requests (<20MB) or file-based (JSONL for large batches). Returns batch job ID and initial status.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Gemini model for content generation | gemini-2.5-flash |
| requests | No | Inline batch requests (for small batches <20MB). Each request should have 'key' and 'request' fields. | |
| inputFileUri | No | URI of uploaded JSONL file (from upload_file tool). Use for large batches or when requests exceed 20MB. | |
| displayName | No | Optional display name for the batch job | |
| outputLocation | No | Output directory for results (defaults to current working directory) | |
| config | No | Optional generation config (temperature, maxOutputTokens, etc.) |
Implementation Reference
- src/types/gemini.ts:134-146 (schema)Type definition for the input parameters (schema) of the batch_create tool, defining the structure for batch creation requests to Gemini API.export interface BatchCreateParams { model: string; requests?: any[]; inputFileUri?: string; displayName?: string; outputLocation?: string; config?: { systemInstruction?: any; temperature?: number; maxOutputTokens?: number; [key: string]: any; }; }