Batch Processing
Made Simple
Reduce AI infrastructure costs by 50% or more. No queues to manage, no minimum volumes — just send requests and get results.
# Load your cargo
curl -X POST https://api.convoy.dev/cargo/load \
-H "Authorization: Bearer $API_KEY" \
-d '{"model": "claude-3", "messages": [...]}'Why Choose Convoy
Infrastructure that gets out of your way so you can focus on building.
Cost Savings
Take advantage of batch pricing without infrastructure complexity. Reduce your AI spend by 50% or more.
Zero Batching Logic
No queues to manage, no timing windows to configure — just send requests and we handle the rest.
No Minimum Volume
Start with one request or send thousands. Convoy scales seamlessly with your workload.
Built-in Reliability
Automatic retry logic and error handling. Your cargo always arrives at its destination.
The Journey: Request to Response
From loading dock to delivery — your cargo is in good hands.
Your App
POST /cargo/load
Queue Staging
Intelligent grouping
Batch (100)
Optimized delivery
Callback
Results delivered
Under the Hood
Built on battle-tested infrastructure for reliability at any scale.
REST API Gateway
A simple, well-documented API. Load cargo with a single POST request and receive a tracking ID instantly.
Intelligent Queue System
Requests are automatically grouped and optimized. No configuration needed — Convoy finds the best batch window.
Temporal Workflows
Durable, fault-tolerant execution powered by Temporal. Every request is tracked, retried, and guaranteed to complete.
AWS Bedrock Integration
Native integration with AWS Bedrock batch APIs. Access the latest models with optimized pricing.
Callback Delivery System
Results are delivered to your webhook as they complete. Real-time updates, zero polling required.
All Aboard?
Ready to simplify your batch processing and start saving on AI costs? Get started in minutes.