Welcome to Spice.ai Cloud

Welcome to the Spice.ai Cloud Platform documentation!

The Spice.ai Cloud Platform is an AI application and agent cloud — an AI-backend-as-a-service with composable, ready-to-use building blocks including high-speed SQL query, LLM inference, vector search, and RAG, built on cloud-scale, managed Spice.ai OSS.

This documentation covers the Spice.ai Cloud Platform.

For the self-hostable Spice.ai OSS runtime, visit docs.spiceai.org.

Projects were previously called apps. These docs use project throughout. The resource is unchanged — only the name is different. The Management API still serves the legacy /v1/apps paths, the OAuth scopes are still named apps:read, apps:write, and apps:delete, and the Terraform provider still uses spiceai_app. See Projects and Management APIs.

:rocket:

Get Started

Sign up and run your first query in minutes

:zap:

Federated SQL Query

Query across any data source with one SQL interface

:robot:

AI Gateway

OpenAI-compatible API for LLM inference

:mag:

Search & Retrieval

Vector and hybrid search for RAG workflows

:plug:

Data Connectors

Connect to 30+ databases, warehouses, and lakes

:bar_chart:

Monitoring

Observe performance with Grafana, Datadog, and more

What You Can Do

With the Spice.ai Cloud Platform you can:

• Query and accelerate data — Run high-performance SQL queries across multiple data sources with results optimized for AI applications and agents.

• Use AI models — Perform LLM inference with OpenAI, Anthropic, xAI, and more for chat, completion, and generative AI workflows.

• Build agentic AI apps — Combine data, models, search, and tools into production-grade AI agent backends.

• Collaborate on Spicepods — Share, fork, and manage datasets, models, embeddings, evals, and tools in a collaborative hub indexed by spicerack.org.

Use Cases

Use Case	Description
Agentic AI Apps	Build AI agent backends with unified data and model access
Database CDN	Cache and accelerate hot data for low-latency applications
Data Lakehouse	Federated queries across warehouses, lakes, and databases
Enterprise Search	Semantic search across enterprise data sources
Enterprise RAG	Retrieval-augmented generation with your own data

Quick Start

Get up and running in minutes:

1. Sign in with GitHub

2. Create a Spice project

3. Add a dataset and query data

4. Add an AI model and chat

Get started API reference

query.py

from spicepy import Client

client = Client("YOUR_API_KEY")
reader = client.query(
    "SELECT * FROM my_table LIMIT 10"
)
df = reader.read_pandas()
print(df)

Community & Support

• Slack — Ask questions and get help from the team at spice.ai/slack.

• GitHub — File issues and contribute at github.com/spiceai/spiceai.

• Enterprise support — Paid plans include priority support with an SLA.

• Help Center — Browse the Help Center for troubleshooting, guides, and FAQs.