Pricing

Start Free. Scale Without Surprises.

No credit card required. No hidden fees. Transparent pricing that grows with you.

Free

$0

All features included. 1 cluster, auto-pauses after 24h. No credit card.

Get Started

Developer

$29/mo + $49/cluster

Always-on standalone clusters. Up to 3 clusters, daily backups, 3 team members.

Get Started

Most PopularTeam

$99/mo + $429/cluster

3-node HA with Raft. Up to 10 clusters, hourly backups, PITR, 99.9% SLA.

Start Free Trial

Business

$299/mo + $899/cluster

VPC peering, LDAP/SSO, plugins. Up to 25 clusters, continuous WAL, 99.95% SLA.

Contact Sales

Enterprise

Custom

Unlimited clusters, dedicated infrastructure, multi-region, custom SLA up to 99.99%.

Contact Sales

Plan Feature Comparison

FeatureFreeDeveloperTeamBusinessEnterprise
Clusters131025Unlimited
Compute per Cluster1 vCPU, 2 GB1 vCPU, 2 GB4 vCPU, 16 GB8 vCPU, 32 GBCustom
Cluster Cost$0 (pauses)$49/mo$429/mo$899/moCustom
Hot Storage Included10 GB10 GB25 GB100 GBCustom
Cold Storage Included50 GB100 GB250 GB1 TBCustom
Connections5001,00010,00050,000Custom
Always-on
Raft HA (3-node)
Read Replicas25Unlimited
BackupsManualDailyHourlyContinuous WALContinuous WAL
Point-in-Time Recovery
VPC Peering
Private Endpoints
LDAP/SSO
GPU / ML / Cache PluginsAdd-onIncluded
Multi-Region
Team Members131025Unlimited
SupportCommunityEmail (48hr)Priority (24hr)Priority (4hr)Dedicated (1hr)
SLA99.9%99.95%99.99%

Compute & Usage Pricing

Platform fee covers your plan. Compute and storage are billed separately based on what you use.

Compute Instances

Per cluster, billed monthly. Choose the right size for each workload.

tc.starter1 vCPU, 2 GB · Standalone · Auto-pauses
Free
tc.developer1 vCPU, 2 GB · Standalone · Always-on
$49/mo
tc.production4 vCPU, 16 GB · 3-node HA · Raft consensus
$429/mo
tc.business8 vCPU, 32 GB · 3-node HA · High performance
$899/mo

Storage & Transfer

Each plan includes storage. Overages billed at these rates per GB/month.

Hot Storage (NVMe)Sub-millisecond reads, in-memory indexes
$0.35/GB
Cold Storage (S3)Seamless query federation, cost optimized
$0.05/GB
Archive StorageCompliance and long-term retention
$0.01/GB
Data TransferEgress between your app and Thermocline
$0.09/GB

Premium Plugins

Supercharge your clusters with powerful plugins. Add or remove at any time.

GPU Acceleration

CUDA-powered vector search

CUDA-based GPU acceleration for HNSW vector similarity search. Batch distance computation, brute-force KNN, graph construction, SQ8 quantized distance, priority scheduling, multi-query batching, and exact re-ranking - all in-process on database nodes with zero network hops.

StandardCore GPU operations with 2 GB VRAM
$799/mo
ProAdvanced GPU operations with 4 GB VRAM
$1499/mo
EnterpriseAll 7 GPU operations with 8 GB VRAM
$3999/mo

ML Engine

In-database machine learning

Run machine learning directly inside your database — 13 algorithms including regression, clustering, classification, dimensionality reduction, anomaly detection, and ensemble methods. Pure Rust, zero external services.

StandardUp to 1M samples, 5K features
$99/mo
ProUp to 10M samples, 10K features
$199/mo
EnterpriseUnlimited samples and features
$299/mo

Intelligent Cache

Adaptive 3-tier caching

Production-grade 3-tier adaptive caching with ML-inspired eviction scoring (7 signals), automatic workload classification (5 classes), and predictive pre-warming. L1 memory, L2 SSD, L3 distributed — sub-millisecond latency, zero config.

StandardL1 + L2 caching with LRU + Frequency eviction
$299/mo
ProML eviction scoring (7 signals) + workload classification
$599/mo
EnterpriseL3 distributed + predictive pre-warming + full tunability
$999/mo

Build AI Applications on a Database That Gets It

One database for your vectors, your context, your agent memory, and your application data. Start free. Scale without limits.

We use cookies to improve your experience and analyze site usage. Read our Privacy Policy for more information.