Free
$0/ month
For developers evaluating grounded retrieval and agents.
- 5,000 queries / month
- 500 documents
- 3 collections
- 2 agents
- Community support
Start with an evaluation. Scale into production.
Choose a self-serve plan or talk to us about private deployment and rollout support.
Pricing plans
Get started free
Pro
$187/ mo, billed annually
Save 3 months free
For teams shipping domain-grounded AI workflows.
- 100,000 queries / month included
- 50,000 documents
- 20 collections
- Unlimited agents
- Adaptive reranking
- Retrieval tuning and evaluation
- Pipelines and webhooks
- $0.80 / 1K queries overage
- Priority support
Enterprise
Custom
For private deployment, enterprise controls, and rollout support.
- Custom query and document limits
- Private VPC or on-prem deployment
- Graph RAG and fine-tuning
- A2A (Agent-to-Agent) protocol
- SSO and audit logging
- Forward Deployed Engineer embedded with your team
- Custom SLA
- Premium support with dedicated CSM
Compare plans
Swipe horizontally to compare all plans.
| Free | Pro | Enterprise | |
|---|---|---|---|
| Search and retrieval | |||
| Semantic search | Included | Included | Included |
| Keyword search (BM25) | Included | Included | Included |
| Hybrid search (RRF fusion) | Included | Included | Included |
| Metadata filtering | Included | Included | Included |
| Adaptive reranking | Not included | Included | Included |
| Retrieval tuning and optimization | Not included | Included | Included |
| Graph RAG | Not included | Not included | Included |
| Ingestion and processing | |||
| PDF, Office, HTML, Markdown, CSV, images | Included | Included | Included |
| Automatic chunking and embedding | Included | Included | Included |
| Near-duplicate detection | Included | Included | Included |
| Document analysis and evaluation | Not included | Included | Included |
| Fine-tuning | Not included | Not included | Included |
| AI and agents | |||
| RAG answer generation | Included | Included | Included |
| Knowledge agents | 2 | Unlimited | Unlimited |
| Pipelines | Not included | Included | Included |
| Webhooks | Not included | Included | Included |
| A2A protocol | Not included | Not included | Included |
| Platform and support | |||
| Dashboard and ops UI | Included | Included | Included |
| Python and TypeScript SDKs | Included | Included | Included |
| REST API | Included | Included | Included |
| SSO (SAML / OIDC) | Not included | Not included | Coming soon |
| Audit logging | Not included | Not included | Included |
| VPC / on-prem deployment | Not included | Not included | Included |
| Forward Deployed Engineer | Not included | Not included | Included |
| SLA | Not included | Not included | Custom |
| Support | Community | Priority | Premium |
Frequently asked questions
What counts as a query?
A single search request to the /search or /search:batch endpoint. Batch search counts each query in the batch individually. RAG answer generation counts as one query. Ingestion, indexing, and analysis do not count.
How does overage billing work on Pro?
Your first 100,000 queries per month are included. Beyond that, additional queries are billed at $0.80 per 1,000 queries, calculated daily and invoiced monthly.
What embedding and reranking models do you use?
We run self-hosted models. Embeddings use EmbeddingGemma-300M and reranking uses Qwen3-Reranker-8B. Your data never leaves our infrastructure for these operations.
What deployment options are available?
Free and Pro run on shared SaaS infrastructure. Enterprise supports private VPC deployment or fully on-premise installation. Contact our team to discuss options for your security and compliance requirements.
Is there a free trial for Pro?
Yes. Pro includes a 14-day free trial with full platform access. No credit card required to start.