Building blocks for data and AI
applications

Composable, ready-to-use data and AI infrastructure — including managed, cloud-scale Spice.ai OSS. Accelerate development of the next generation of intelligent software.

Trusted by

Introducing Spice.ai

An enterprise-grade solution from Spice AI, Spice.ai delivers planet-scale data and AI infrastructure in a fraction of the time to build in-house and at a fraction of the cost.

Spice.ai provides building blocks for creating data and AI-driven applications by composing real-time and historical time-series data, ETL, machine learning training and inference, in a single, interconnected AI backend-as-a-service. Run Spice.ai at peak performance with managed, cloud-scale Spice.ai OSS, complete with enterprise support.

Spice dashboard with playground tab selected
  • No need to self-host with managed, cloud-scale, Spice.ai OSS, the best place to run Spice.ai OSS.

  • No need to build and operate complicated infrastructure.

  • No need to operate ETL, big data systems, machine learning pipelines, and caching and query engines — the list goes on.

  • No need to manage 10s -100s of TBs of data.

  • No need for an expensive SRE or Ops teams.

  • No need to be data science and machine learning experts to leverage AI and time-series data.

Powered by

Building Blocks of Intelligent Apps

With Spice.ai, building blocks for creating the next generation of apps are within reach for any developer. Incrementally adopt the blocks you need, then compose them together to develop intelligent web3 data and AI-driven software.

Data

  • SQL query

  • Managed Spice.ai OSS

  • Datasets and views

Spice.ai provides federated SQL query, local materialization, and acceleration of datasets from any database, data warehouse, or data lake.

SQL Query

Query data using simple SQL in seconds, and fetch results in JSON or Apache Arrow for easy use with apps, machine learning, or libraries, including NumPy and Pandas.

AI

  • ML model training and registry

  • ML model hosting and inferencing

Spice.ai includes machine learning pipelines that are automatically wired up to a petabyte-scale data platform, providing high-quality time-series data for feature extraction and storage, training, and inferencing.

Trained Models

Easily share your models privately with collaborators or publicly, and access those developed by the community. All trained models are tracked in the Spice model registry and can be used without additional user-provided data.

Graphic with SQL Query, Results Apache Arrow APIs

Enterprise-Grade Performance

ApacheArrow APIs

High performance, high availability, and fully compliant, Spice.ai is the first service to deliver developer-friendly, planet-scale data over Apache Arrow APIs. Query and fetch millions of records in seconds.

Dedicated to the Developer Experience

Get Started with Just Three Lines of Code

Get started in minutes, not months. With Spice.ai, it takes just three lines of code to get rich data in familiar tools like NumPy, Pandas, and PyTorch. Developer-friendly Node.js, Go, Python, and Rust SDKs make accessing and using petabyte-scale data easy.
Code snippets with just a few lines of code to install
Spice dashboard with HTTP request, code snippet and responde

Designed for Applications & Machine Learning

Build the Next Generation of Apps

Designed for applications and machine learning, Spice.ai gives you the tools and technology to focus on your core business and build the next generation of apps.

Try Spice.ai Now

Query time-series data in seconds & make ML predictions

Powered by

Discover just how fast querying Spice.ai is, and make AI predictions via our live widget, powered by Spice Firecache. Dedicated to delivering the best experiences for developers, we enable you to get what you need within a few clicks.

Sign up with Spice.ai to unlock full planet-scale SQL query and machine learning capabilities today.

Try for Free

How Spice.ai
Works

Focus on your application. Spice.ai brings together enterprise-grade data and AI infrastructure, serverless compute, storage, ZK & ML GPU clusters, blockchain nodes, and indexing into a single, developer-focused platform.

SDKS
Node.js SDK
Python SDK
GO SDK
Rust SDK
More SDKs coming soon
Example Ecosystem Libraries
Pandas
PyTorch
Tensor Flow
Compatible with many more
Building blocks for creating data and AI-driven apps
Data
AI
Compute
Storage
Blockchains
ZK & ML Accelerators
Blockchain Nodes
Ethereum
Polygon
Bitcoin
OP Stack
Private ZK Node Clusters
1TB Ram
8x GPU
Many more
AI Infrastructure
Real-Time Data
Indexing • SQL Query • Firecache
Complete
Historical Data
Indexing • SQL Query • Firecache
Hosted AI & ML
ML Pipelines • Inferencing
Models
Compute
Functions • Actors
Storage
DuckDB • Blob
AI Models
Predictions
Community Data
Create Your Own
DeFi
Uniswap • Sushiswap • Aave
NFTs
NFT Metadata • NFT Owners
Contract Indexing
Token Prices
ENS
Wallet Balances
Native token balances
More coming soon
AI Features
Training
Inferencing
Model Registry
Acceleration Clusters
1st part of diagram with enterprise-grade
Pandas
Web3.js
PyTorch
Tensor Flow
Compatible with many more
Data
AI
Compute
Storage
Blockchains
ZK & ML Accelerators
Ethereum
Polygon
Bitcoin
OP Stack
Flow
1TB Ram
8x GPU
Many more
Real-Time Data
Indexing • SQL Query • Firecache
Complete
Historical Data
Indexing • SQL Query • Firecache
Hosted AI & ML
ML Pipelines • Inferencing Models
Compute
Functions • Actors
Storage
DuckDB • Blob
AI Models
Predictions
Create
Your Own
DeFi
Uniswap • Sushiswap • Aave
NFTs
NFT Metadata • NFT Owners
Contract
Indexing
Token Prices
ENS
Wallet Balances
Native token balances
More coming soon
Training
Inferencing
Model Registry
Bare-Metal ZK/ML Acceleration
GPUs
FPGAs (Coming soon)
Spice AI
Multi-cloud, high-availability SOC2* deployments
Building & Operating In-House
Data
Enriched Datasets
Spice AI supportedProcess and enrich manually
Historical prices data
Included
$1K - $15K per month
From providers such as CoinMarketCap
Managed Infrastructure
Data & AI Infrastructure Cost
Included$5k to $50k
per month
Enterprise-grade high-availability and compliance
Included in Enterprise
Multi-cloud, high-availability SOC2* deployments
Twice as much as Spice.ai
2x the total cost of infra and ops
Web3 Node &‍ Indexing Cost
Included
$1k to $5k
per month, per blockchain or data source
High-performance caching for frontend & inferencing queries
Managed Spice.ai OSS
$1k to $5k
per month
Engineering
Data and Infrastructure Engineering Cost
Included$15k to $20k
per month, per engineer
Time to Implement
Get started in minutes
Typically 3 to 6 months
Operations & Support
On-Going Operational Cost
Included
with Pro for Teams and Enterprise plans
$15k
per month, per engineer
99.9%+ Enterprise SLA & Support
Included in Enterprise
Self-managed 24/7 on-call
Spice.ai vs. Building Yourself
Testimonials goes here.
"Initially, we thought it's such a departure from where they are, it's going to take them a long time. But in a few weeks, it's like magic. We had everything working exactly as we wanted, and it's amazing."
Sreeram Kannan
Founder and CEO of EigenLayer
"Nethermind is committed to advancing the Ethereum re-staking ecosystem. We're excited that our re-staking dashboard, an early contribution to the EigenLayer community, now thrives on data powered by Spice AI."
Eliot Stock
CPO of Nethermind
"Other solutions were prohibitively expensive - what we could do in Spice with a single query would have taken millions of API calls in other platforms."
Andrew Dworschak
CEO & Co-founder of Yakoa
“We are a team of crypto and fintech product experts, not cloud and developer infrastructure , so we needed to evaluate solutions based on their ease of implementation and time to market. We value solutions that deliver performance of transactions and pricing data without compromising the developer experience
and accuracy.”
Kareem Khattab
CEO and Founder of Entendre
“Spice AI makes it insanely easy for to leverage high quality, reliable datasets on our platform. This is critical for our developers to gain insight into how the APIs are being used so we can enable Web3 developers to build their first dApp in minutes.”
Anir Agarwal
Founder and CEO of Niftory
“XMTP is enabling web3 messaging between wallets. Spice enables us to leverage the rich Python ecosystem of data science and ML tools to build the best web3 data-driven experiences possible.”
Peter Denton
Head of Growth, XMTP
arrow icon pointing left
arrow icon pointing right

Core Features
of Spice.ai

Combine data with code and machine learningto build the world’s next top data and AI-driven applications.

Enterprise-Grade Infrastructure

Spice.ai is built for enterprise, 99.9%+ high-availability, security, performance, and compliance backed by an enterprise-level SLA and support. SOC 2 Type II certified.

Apache Arrow

Access developer, ML, and Data-Science friendly APIs with HTTP and Apache Arrow Flight (gRPC) endpoints. Query across multiple chains and datasets with filtering and aggregation in seconds.

Enriched Data Included

High-quality, enriched datasets from tokens, NFTs, and DeFI to restaking, ENS, and more.

Combine SQL with code

Use developer-friendly SDKs to query web3 data with ease, including joins across multiple datasets with filtering and aggregations, in just three lines of code.

Ecosystem Compatible

Fetch millions of rows of data and use libraries such as NumPy, Pandas, Tensorflow, and PyTorch with ease. For web3 data, use client libraries such as web3.js, ethers.js, and web3.py in combination with SQL query APIs.

Datasets & Views

Define and create your own private datasets and views, available in SQL query and Spice Firecache, and optionally shareable with anyone else.

SQL Firecache

Cache datasets for high concurrency and blazing fast SQL query up to 10x the performance of general SQL query, backed by cloud-scale hosted DuckDB instances.

Serverless Functions

Write code hosted on Spice AI and co-located with your data, executed on every block in Go or Python.

Petabyte-Scale Data For Applications & ML

Spice.ai is the fastest way to access real-time, time-series data. Get millions of records in seconds.

Private ZK/ML Cluster

Deploy and run managed, baremetal ZK and ML-capable Kubernetes clusters with ease, and let the Spice AI team take care of painful 24/7 operations.
arrow icon pointing left
arrow icon pointing right

Building the Future of Data & AI-driven Apps Together

We're building the Spice AI Platform, so that developers everywhere can have the building blocks to create the next generation of intelligent applications with ease. Learn more about the platform, where it's going, and how you can be a part of it.