Accelerated Block Storage illustration

Accelerated Block Storage (ABS)

High-performance block storage with sustained IOPS for real-time workloads.

What is ABS?

Shared, persistent storage decoupled from compute.

Sustained IOPS for I/O-intensive workloads.

Elastic scale with zero downtime. No hardware changes or re-provisioning required.

Part of Nirvana performance cloud stack: Compute + Storage + Networking.

Storage stack illustration showing Orchestration, Networking, Storage, and Compute layers

Performance Specification

Designed for data heavy, I/O-intensive real-time workloads.

Storage spec icon

20,000 Baseline IOPS

Storage spec icon

600,000 Burst IOPS

Storage spec icon

Latency: Sub-ms

Storage spec icon

Throughput: 1.6 GB/s writes, 260–380 MB/s sustained, ~600 MB/s reads

Storage spec icon

Volume Size: 36 GB to 4 Petabyte

Storage spec icon
Nirvana Labs

P99 Latency Guarantees

Product Highlights

High IOPS, Low Latency

Sustained Performance

No throttling after 2–3 hours like traditional cloud. Stay fast as long as your workload stays hot.

High Availability

Data is never tied to a specific server. If a node fails, workloads migrate instantly without rebuild or data loss.

Elastic Scale

Scale from 32 GB to 4 PB with zero downtime. No hardware changes or re-provisioning required.

Low Latency

P99 latency guarantees and durability, without fluctuation during usage spikes.

Colocation with Compute

Tightest physical data path (never shared) with Nirvana bare-metal compute for ultra-low latency.

Predictable Pricing

Flat, TB-based pricing (~$94/TB/Month) with IOPS performance included. No burst credits, no metering.

Product highlights illustration

Use Cases

Vector Databases

High-IOPS storage for embedding AI search, RAG pipelines, and similarity workloads.

Gaming

Game backend databases, game telemetry and event pipelines

High IOPS Databases

OLTP workloads, Clickhouse, Postgres, ElasticSearch

Blockchain Infrastructure

Archive nodes, ETL pipelines, indexing

Agent Sandboxes

Isolated, high-performance environments for autonomous agents and long-running inference tasks.

Real-Time Analytics

Streaming pipelines, OpenSearch, and data-intensive workloads.

Powering AI, blockchain, and
real-time systems.

Talk to Sales