Welcome to Spice.ai | Spice.ai Cloud Documentation

For the complete documentation index, see llms.txt. This page is also available as Markdown.

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.

Get Started

Sign up and run your first query in minutes

Federated SQL Query

Query across any data source with one SQL interface

AI Gateway

OpenAI-compatible API for LLM inference

Search & Retrieval

Vector and hybrid search for RAG workflows

Data Connectors

Connect to 30+ databases, warehouses, and lakes

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 app
3. Add a dataset and query data
4. Add an AI model and chat

Code Example

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.