Simple, transparent pricing
Start free. Scale with your team. Pay only for what you use beyond your plan.
Developer
Build and experiment. Rates apply after limits are reached.
Included
Executions
500 / mo
Pipelines
2
Storage
1 GB
Memories
100
Memory retrievals
1,000 / mo
Support
Community
Overage rates
Per execution
$0.04
Per pipeline
$5.00
Per GB storage
$0.40 / mo
Per memory stored
$0.03
Per 1K retrievals
$1.00
Startup
For small teams shipping AI agents to production.
Included
Executions
3,000 / mo
Pipelines
15
Storage
10 GB
Memories
1,000
Memory retrievals
10,000 / mo
Webhooks
Included
Support
Email (48hr)
Overage rates
Per execution
$0.03
Per pipeline
$4.00
Per GB storage
$0.30 / mo
Per memory stored
$0.02
Per 1K retrievals
$0.80
Business
For growing teams scaling production workloads.
Included
Executions
15,000 / mo
Pipelines
100
Storage
50 GB
Memories
10,000
Memory retrievals
100,000 / mo
Webhooks
Included
Scheduling
Included
Support
Priority (12hr)
Overage rates
Per execution
$0.02
Per pipeline
$3.00
Per GB storage
$0.20 / mo
Per memory stored
$0.01
Per 1K retrievals
$0.60
Enterprise
For large teams requiring dedicated infrastructure and SLAs.
Included
Executions
100,000 / mo
Pipelines
750
Storage
500 GB
Memories
100,000
Memory retrievals
1,000,000 / mo
Webhooks + Scheduling
Included
Uptime SLA
99.9%
Dedicated infrastructure
Included
Support
Dedicated (4hr)
Overage rates
Per execution
$0.01
Per pipeline
$2.00
Per GB storage
$0.01 / mo
Per memory stored
$0.01
Per 1K retrievals
$0.50
FAQ
What counts as an execution?
Every agent or workflow run counts as one execution, regardless of how long it takes or how many LLM calls it makes internally.
What happens when I exceed my plan limits?
Your agents continue running. Overage usage is billed at the per-unit rates shown on your plan and added to your next monthly invoice.
Can I upgrade or downgrade at any time?
Yes. Plan changes take effect at the start of your next billing cycle. Upgrading mid-cycle prorates the difference.
Is the Developer tier free?
The Developer tier has no monthly subscription fee and includes 500 executions, 2 pipelines, and 1 GB of storage. If you exceed those limits, standard overage rates apply — so usage beyond the included amounts is not free.
What are memories and retrievals?
Memories are persistent key-value or vector entries your agents can store and query across runs. Retrievals are semantic search queries against those stored memories.
Can I use the SDK locally for free?
Yes. The daita-agents Python package is free and open source. You only pay for cloud deployments, managed pipelines, and storage.
Ready to get started?
Start free and scale as you grow. No credit card required.
Production AI agent framework with zero-config observability and managed cloud deployment.
© 2026 Daita Corp. All rights reserved.