Pricing

Pay only for what you use.

Wallet-based metered pricing across the entire substrate -- Records, KG, Causal, Analogy, and the Pinecone-compat memory layer -- one ledger, sub-cent precision, no per-namespace fees, no per-seat fees, no minimums.

How it works

  1. Sign up. You get $5 of free credit.
  2. Top up your wallet via PayPal -- $10, $25, $100, $500, or any custom amount.
  3. Use the API. Every operation is metered and deducted from your wallet in real time. The dashboard shows the per-op ledger.
  4. We email you when your balance drops below $5. Auto-topup optional.
  5. Cancel anytime. Any unused balance is refundable for 30 days.

Unit rates

OperationRateWhat you'd otherwise pay
Records -- the primary substrate
records_ingest (typed event + auto-embed)$2.00 / 1MMem0 Pro caps at 500k records / mo for $249
Zep $125-375/mo flat tiers
records_query (semantic + typed filters)$2.00 / 1MLangSmith $500 / 1M traces (capture-only)
Pinecone serverless ~$17 / 1M reads
records_timeline / records_get$0.50 / 1M--
records_forget / records_deleteFreeGDPR ops should never be metered.
.neruva export / import (atomic backup)10 / mo free, then $0.10 / opNo vendor offers atomic single-file substrate export.
HD substrate -- nobody else offers any of these
HD KG add / query / stats$0.50 / 1Mnot offered
HD analogy (A:B::C:?)$0.50 / 1Mnot offered
HD causal (observe / intervene)$1.00 / 1Mnot offered
Pinecone-compat memory -- migration on-ramp
memory_upsert / memory_query$2.00 / 1MPinecone $4 / 1M write, $17 / 1M read
memory_fetch / memory_update$0.50 / 1MPinecone $2-4 / 1M
memory_delete / memory_forget_whereFree--
Storage
Records / vectors (1-bit packed)$0.10 / GB / moPinecone $0.33 / GB / mo
Weaviate $0.255 / GiB / mo
Chroma $0.33 / GiB / mo
EgressFreeChroma charges $0.09 / GiB egress

No per-namespace fees. No per-seat fees. No per-pod fees. No minimums. The HD substrate operations replace LLM calls for the substrate-answerable slice of agent workloads, so the relevant comparison there is per-1M-token cost on a frontier model -- which runs orders of magnitude higher.

What you'd pay for the equivalent stack

A Series-A startup with 100 production agents typically wires up three tools: a vector DB for memory, an observability platform for captured turns, and a cross-session memory product. We replace all three. Workload assumed: 500k records/day, 2M queries/day, 5GB storage.

LayerVendorMonthly
Vector memoryPinecone Serverless~$1,087
Observability / captureLangSmith Plus + per-trace~$30,112
Cross-session memoryMem0 Pro (cap exceeded; Enterprise needed)$249+
Equivalent stackthree vendors, three bills, no KG / causal / analogy~$31,448 / mo
Neruvaone vendor, one wallet, all four substrate layers~$150 / mo

Sources: pinecone.io/pricing, langchain.com/pricing, mem0.ai/pricing. Swapping LangSmith for Helicone Team ($799 flat) drops the bundle to ~$2,135/mo -- still 14x our rate, and you lose per-trace fidelity. The bundle does not include KG, causal, or analogy -- those have no comparable in any other product, at any price.

Plus: stop burning input tokens on context-stuffing.

Most agent stacks "remember" by re-prepending recall text to every LLM call. That recall slice gets billed at frontier-model input rates, every turn, forever. Replace it with one records_query.

The slow way
Stuff 5 KB of recall context into every Opus 4.7 turn.
~1.25k input tokens × $5/M = $0.00625 / turn
Neruva
One records_query with typed filters. Returns the same 5 KB.
$2 / 1M = $0.000002 / turn
Net savings
Per turn: ~3,000x cheaper.
A 1k-turn-per-day agent saves ~$190/mo on the recall slice alone.
The HD substrate angle

An HD causal do(X) query at $1 / 1M replaces a multi-step LLM reasoning chain (~5k input + 1k output ≈ $0.05 / call on Opus 4.7). That's ~50,000x cheaper for substrate-answerable questions -- and you gain determinism, replayability, and no temperature noise.

The unit economics of memory

Deposit cost ≈ 1 call. Recall cost ≈ 1 call. At $2 / 1M ops, that's effectively $0.000004 for a write-then-read round trip. A single high-quality mistake-record can save 15-60 minutes of re-debugging the next time the agent encounters the same root cause. The discipline is one line: deposit at every seam, compact when noise creeps in. The substrate doesn't fire in the inner write--run--fix loop -- it fires at the boundaries where context would otherwise be lost.

What you actually pay

Solo agent
free

10k records/day, 50k queries/day, 100MB storage. One autonomous coding agent running 24/7. Fits inside the $5/mo free credit.

Series-A startup
~$150/mo

500k records/day, 2M queries/day, 5GB storage. 100 agentic users in production. ~200x cheaper than the equivalent Pinecone + LangSmith + Mem0 stack.

Growth
~$3k/mo

10M records/day, 40M queries/day, 200GB storage. Equivalent three-vendor stack: ~$60-380k/yr depending on observability tier.

Always free

Delete / forget
GDPR ops never metered. Forget by id, predicate, or namespace.
Schema queries
list_indexes, describe_index, stats, records_stats.
Egress
No per-GB egress fees. Pull your data freely.
Namespaces
Spin up a million. No per-namespace fee, ever.

Enterprise

Volume discounts at $1k/mo committed (-20%), $5k/mo (-40%), and $20k/mo (-60%). For dedicated capacity, VPC peering, SOC 2 audit support, or on-prem deployment, contact info@neruva.io.