Build and experiment. Rates apply after limits are reached.
Included
Overage rates
For small teams shipping AI agents to production.
Included
Overage rates
For growing teams scaling production workloads.
Included
Overage rates
For large teams requiring dedicated infrastructure and SLAs.
Included
Overage rates
Every agent or workflow run counts as one execution, regardless of how long it takes or how many LLM calls it makes internally.
Your agents continue running. Overage usage is billed at the per-unit rates shown on your plan and added to your next monthly invoice.
Yes. Plan changes take effect at the start of your next billing cycle. Upgrading mid-cycle prorates the difference.
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.
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.
Yes. The daita-agents Python package is free and open source. You only pay for cloud deployments, managed pipelines, and storage.
Start free and scale as you grow. No credit card required.