AnvaiOps
Free Trial
$0 / 30 days
Try one real workflow.
- 1 GB knowledge storage included
- 10,000 searches / month included
- 1 connector included
Pricing
Start trial
Choose Team
Choose Pro
Get started
Contact us
Start small. Build on what you learn.
Find the right starting point for your team. Bring a workflow — we’ll help you map the fit.
Team
$19+ / mo
For solo builders and small teams.
- 3 GB knowledge storage included
- 30,000 searches / month included
- 2 connectors included
Pro
$199+ / mo
Connect the knowledge across your team.
- 30 GB knowledge storage included
- 100,000 searches / month included
- 6 connectors included
Business
$599+ / mo
Bring more teams and sources together.
- 100 GB knowledge storage included
- 300,000 searches / month included
- All 21 catalog connectors included
Enterprise
$1,500+ / mo
Plan for your scale and requirements.
- 250 GB knowledge storage included
- 1,000,000 searches / month included
- All 21 catalog connectors included
Base fees include the displayed allowances. Business and Enterprise include all 21 catalog connectors; usage above storage, search, ingest and embedding allowances is metered separately. Network transfer and optional add-ons may also apply. Enterprise infrastructure is quoted separately. Preview availability is confirmed with our team.
Compare plan details
Included allowances and capability availability by plan. Beta and preview capabilities are labeled below.
Free Trial
$0 / 30 days
Evaluate the workflow with capped usage and shared compute. No production SLA — built for fast proof-of-value before paid rollout.
- 1 GB indexed storage included
- 500 MB ingest/mo (write-once)
- 100 MB managed embedding included
- 10,000 queries/mo included
- 50 GB object reads/mo included
- 10 TB/mo logical scan guardrail (not billed)
- 1 connector
- Shared cluster — single region
- Standard retrieval quality
- Community docs + Slack forum
- Expires after 30 days
ProximaDB capabilities
- Vector Search GA
- Hybrid Retrieval Beta
- Federated SQL Beta
- Document CRUD Beta
- ORION Graph Beta
- Observability Runtime Beta
- Security Runtime Beta
- Time Series (TST) Experimental
- Event Sourcing Experimental
- Distributed Compute Experimental
- DataFusion OLAP Experimental
- Code Embeddings Experimental
Team
$19+ / mo
Self-serve on-ramp for solo engineers and small teams. Real connectors, real allowance, real workflow — at a try-it-yourself price.
- 3 GB indexed storage included
- 1.5 GB ingest/mo (write-once)
- 300 MB managed embedding included
- 30,000 queries/mo included
- 150 GB object reads/mo included
- 30 TB/mo logical scan guardrail (not billed)
- 2 connectors
- Async ingest only
- Standard retrieval quality
- Pooled cluster — single region
- Self-serve docs + community forum
ProximaDB capabilities
- Vector Search GA
- Hybrid Retrieval Beta
- Federated SQL Beta
- Document CRUD Beta
- ORION Graph Beta 🔒 Preview
- Observability Runtime Beta 🔒 Preview
- Security Runtime Beta
- Time Series (TST) Experimental 🔒 Preview
- Event Sourcing Experimental
- Distributed Compute Experimental
- DataFusion OLAP Experimental
- Code Embeddings Experimental
Pro
$199+ / mo
Production-ready teams with multiple sources. Enhanced retrieval, sync ingest, dedicated Slack channel, optional DR.
- 30 GB indexed storage included
- 15 GB ingest/mo (write-once)
- 3 GB managed embedding included
- 100,000 queries/mo included
- 1500 GB object reads/mo included
- 300 TB/mo logical scan guardrail (not billed)
- 6 connectors
- Async + sync ingest ($8.25/GB sync embedding overage)
- Enhanced retrieval quality (multilingual)
- Pooled cluster — single region
- DR add-on available (+$49/mo)
- Dedicated Slack support channel
ProximaDB capabilities
- Vector Search GA
- Hybrid Retrieval Beta
- Federated SQL Beta
- Document CRUD Beta
- ORION Graph Beta
- Observability Runtime Beta
- Security Runtime Beta
- Time Series (TST) Experimental 🔒 Preview
- Event Sourcing Experimental 🔒 Preview
- Distributed Compute Experimental 🔒 Preview
- DataFusion OLAP Experimental 🔒 Preview
- Code Embeddings Experimental 🔒 Preview
Business
$599+ / mo
Production workflow at BU scale. All 21 connectors, real-time webhook ingestion, retrieval analytics, NBD response target.
- 100 GB indexed storage included
- 50 GB ingest/mo (write-once)
- 10 GB managed embedding included
- 300,000 queries/mo included
- 5000 GB object reads/mo included
- 1 PB (1,000 TB)/mo logical scan guardrail (not billed)
- All 21 connectors
- Async + sync ingest ($8.25/GB sync embedding overage)
- All 21 connectors
- Enhanced retrieval quality (multilingual)
- Pooled cluster — single region
- DR add-on available (+$99/mo)
- Real-time webhook ingestion (Slack + Teams)
- Slack bot (/anvai command) + Teams bot
- MTTR + retrieval analytics
- Dedicated Slack support channel
- Next-business-day response target
ProximaDB capabilities
- Vector Search GA
- Hybrid Retrieval Beta
- Federated SQL Beta
- Document CRUD Beta
- ORION Graph Beta
- Observability Runtime Beta
- Security Runtime Beta
- Time Series (TST) Experimental
- Event Sourcing Experimental
- Distributed Compute Experimental 🔒 Preview
- DataFusion OLAP Experimental 🔒 Preview
- Code Embeddings Experimental 🔒 Preview
Enterprise
$1,500+ / mo
Dedicated capacity for higher-scale or regulated environments. Private VPC, SSO, Managed Success, custom SLA.
- 250 GB indexed storage included
- 125 GB ingest/mo (write-once)
- 25 GB managed embedding included
- 1,000,000 queries/mo included
- 12500 GB object reads/mo included
- 2 PB (2,500 TB)/mo logical scan guardrail (not billed)
- All 21 connectors
- Async + sync ingest — sync SLA negotiable
- Premium retrieval quality · bring-your-own-model available
- All 21 connectors
- Dedicated capacity profile — infrastructure quoted by cloud and region
- DR orchestration included — storage and transfer metered
- Private VPC / intranet deployment
- SSO (Okta, Azure AD)
- Audit logs + RBAC
- Managed Success included
- Monthly optimization + retrieval quality reviews
- Custom SLA
ProximaDB capabilities
- Vector Search GA
- Hybrid Retrieval Beta
- Federated SQL Beta
- Document CRUD Beta
- ORION Graph Beta
- Observability Runtime Beta
- Security Runtime Beta
- Time Series (TST) Experimental
- Event Sourcing Experimental
- Distributed Compute Experimental
- DataFusion OLAP Experimental
- Code Embeddings Experimental 🔒 Preview
Estimate usage and monthly cost
No seat-based pricing
Add ten engineers to your support team — your platform bill doesn't move. Charges track compute consumption, not headcount.
Pooled by default
Lower tiers share compute while tenant data stays isolated and metered separately. Dedicated capacity is reserved for Enterprise isolation, private networking, or sustained high-volume workloads.
Ingest is write-once
You pay once per GB ingested to index content. Bring your own vectors to skip managed embedding, or let AnvaiOps embed documents for you. That cost is amortized across every future retrieval that benefits from it.
Search billed on what it actually reads
Retrieval billing is a flat per-query rate plus the bytes your queries actually fetch from object storage — not your total corpus, and not the data logically examined. Compressed indexes and caching keep physical reads tiny; metadata filters (team, severity, date) and multiple named indexes cut them further.
Cloud scenarios are planning estimates. Deployment availability and infrastructure pricing are confirmed with your quote.
Cloud platform:
ECS Fargate + S3
Select a paid plan to estimate usage above its allowances without automatically changing plans. Trial usage is capped; very large workloads require a quote.
Estimate your monthly cost
+$49/mo Pro DR add-on
+33% on ingest — records searchable in under 2 seconds (Pro tier and above; lower tiers ingest async)
Estimates use GB-based meters. Actual storage footprint varies with embedding model and dimension, metadata volume, chunking, data distribution, indexes, replicas, and schema. In SaaS, AnvaiOps manages the storage schema and operational layout; customers control source data, metadata, collection/index choices exposed by API, vector-import or managed-embedding options, filters, and ingest/query parameters.
Pro
~$199 / mo
Shared compute included · data meters apply
Platform: Pro · Compute: pooled AKS
Included: 30 GB storage · 100,000 searches · 1.5 TB object reads · 6 connectors
Data meters: retrieval (queries + physical bytes) · storage (GB-month) · ingest/indexing (GB) · embedding (GB) · network egress
Get exact quote
Included: 30 GB storage · 100,000 searches · 1.5 TB object reads · 6 connectors
Data meters: retrieval (queries + physical bytes) · storage (GB-month) · ingest/indexing (GB) · embedding (GB) · network egress
View usage rates and billing
Consumption meters
Plan fees include shared compute and tier-appropriate support. Tenant-specific storage, search I/O, ingest, and outbound data are metered after included allowances.
Metered usage is denominated in one consumption unit — the AnvaiOps Unit (AOU), where 1 AOU = $0.01 of list-rate consumption. Every plan prices the AOU at $0.01, so the dollar rates below are the AOU rate × 100.
| Meter | Unit | Rate | What drives it |
|---|---|---|---|
| RetrievalPrimary | per M queries + per TB physically read | $50/M + $0.05/TB | You're billed a flat per-query rate plus the bytes your queries actually fetch from object storage — not the size of your knowledge base, and not the data your query logically examined. Compressed indexes and caching mean a query typically reads a fraction of a percent of your corpus; cached queries read almost nothing. Example: 100,000 queries/mo on a 30 GB corpus ≈ $5.00 flat + pennies of physical scan. Metadata filters and multiple named indexes reduce reads further. Team includes 30,000 queries + 150 GB physical scan/mo; Pro includes 100,000 queries + 1500 GB physical scan/mo; Business includes 300,000 queries + 5000 GB physical scan/mo. |
| Storage | per GB-month of your data | $0.020 | Persistent searchable incident knowledge, billed on your data as written — the raw GB you ingest, at a predictable raw-GB rate. Indexes, compression, metadata, and replicas are included; you never pay for the engine's footprint. Cross-region DR replication is billed only when selected or included by tier. Billed on raw source bytes so a 200KB Confluence page is billed fairly against a 20KB Jira ticket — and the bill never moves when the engine changes its storage layout. This is managed searchable knowledge, not raw object storage. |
| Ingest / IndexingAOU | per GB indexed | $0.75 BYO vectors or document payload |
Write, validate, index, and compact customer-supplied content or vectors. v1/v2 vector batch APIs accept embedded vectors; v3 documents can also carry vectors through ProximaDB.Included ingest scales by tier from 1.5 GB on Team to 50 GB on Business. Ongoing retention is covered by the storage meter. |
| Managed EmbeddingAOU | per GB embedded | $5.00 $8.25 sync · BGE -25% · large $26.25 / $52.50 |
Optional embedding performed by AnvaiOps when you send documents without vectors. Async uses batched OpenAI text-embedding-3-small by default; hosted BGE models are available at 25% below the comparable OpenAI lane. Sync is available on Pro and above for immediate searchability. Small managed embedding allowances are included by tier. Native document ingest is $5.75/GB async when native ingest and OpenAI embedding consumption are used together, or $4.50/GB with hosted BGE. OpenAI text-embedding-3-large is available as a premium managed embedding option. Teams that bring precomputed vectors pay no embedding consumption. |
| Extra Connector | per connector / mo | $39 | For paid plans with a connector allowance, additional catalog connectors are charged monthly. Ingest, storage and search are separate usage meters. All 21 catalog connectors are included in Business and Enterprise — no additional per-connector fee within the current catalog. Data usage remains metered. Inclusion does not change a connector’s release status; see Integrations. |
| Network Egress | per billable GB | cloud nominal rate | Outbound transfer for result exports, cross-cloud access, on-prem access, and selected DR replication. Provider free allowances and same-cloud paths are reflected in the calculator. Network transfer is tenant-specific even when compute is pooled. |
Introductory rates use pooled compute to keep entry pricing low. Tenant data remains isolated and is billed through measured meters: retrieval (queries plus object-store bytes actually read), ingest/indexing (GB indexed), managed embedding (GB embedded), and storage (raw GB-month). Logical scan volume remains a fair-use guardrail and is not billed. Network egress is shown separately at the applicable cloud rate. Dedicated Enterprise pricing starts at $1,500/mo and is quoted with its required infrastructure, region, and SLA.