When to Use Batching
- Bulk operations - Process 10-100 research queries at once
- Shared settings - Apply the same mode, output formats, and search filters to all tasks
- Unified tracking - Monitor progress and costs across all tasks in one place
For individual tasks with unique configurations or advanced features (files, deliverables, MCP servers), use the standard DeepResearch API instead.
Quick Example
Batch Lifecycle
| Status | Description |
|---|---|
open | Batch created, ready to accept tasks |
processing | Tasks are queued, running, or completed |
completed | All tasks finished successfully |
completed_with_errors | All tasks finished, some failed |
cancelled | Batch was cancelled |
Retrieve Results
Next Steps
Complete Guide
Full batch documentation with search configuration, webhooks, and best practices
Python SDK
Complete Python SDK reference for batch operations
TypeScript SDK
Complete TypeScript SDK reference for batch operations
API Reference
REST API endpoint documentation

