Ir al contenido
AI.info

AI Tools

Chroma

Chroma: precios, capacidades, actualizaciones y alternativas, leídos en las páginas del propio desarrollador.

El sitio web de Chroma

En inglés

Key facts

Price
Paid plans: see pricing Read on trychroma.com
Free plan
No Read on trychroma.com
Platforms
Web · CLI · API
API
Yes
Open source
Yes · Apache-2.0 Read on github.com
Certifications
SOC 2 Type II Read on trychroma.com
Prices checked
10 Nov 2026 Read on trychroma.com

ChromaDB stores and searches data for AI applications. It supports vector, sparse-vector, full-text, regex, and metadata search, and can run locally or as a managed cloud service. Developers use it to retrieve relevant documents for search, retrieval-augmented generation, and agent workflows.

ChromaDB is open source under Apache 2.0; it is search infrastructure, not an AI model. Chroma’s pricing page lists usage-based Cloud plans, but the company has announced that Cloud writes will stop on December 7, 2026, and reads on December 22, 2026. Open-source ChromaDB continues.

Category
Developer Tools
Read from the maker’s pages
2026-11-18

Company

Chroma Inc.

Features

  • Search with dense and sparse vectors, including BM25 and SPLADE
  • Run full-text, trigram, and regex searches
  • Filter and facet results using metadata
  • Combine search methods through a query interface
  • Fork collections for dataset versioning, testing, and roll-outs
  • Use a command-line interface for development
  • Run locally with pip, npm, or Docker
  • Open source under the Apache 2.0 license

Use cases

  • Build document retrieval for a retrieval-augmented generation app
  • Find relevant records to provide context to an AI agent
  • Search documents using both keyword and semantic matching
  • Filter search results by document metadata
  • Test changes to datasets by forking collections

Pricing

Paid plans: see pricing

Prices checked
2026-11-10

Starter

$0/mo

  • $0 /month
  • $2.50 per GiB written
  • $0.33 per GiB per month
  • $0.0075 per TiB queried
  • $0.09 per GiB returned
  • 10 databases
  • 10 team members
  • Community Slack

Team

$250/mo

  • $250 /month
  • $2.50 per GiB written
  • $0.33 per GiB per month
  • $0.0075 per TiB queried
  • $0.09 per GiB returned
  • 100 databases
  • 30 team members
  • Slack support
  • SOC II
  • Volume-based discounts

Enterprise

price on request

  • Unlimited databases
  • Unlimited team members
  • Dedicated support
  • Single tenant clusters
  • SLAs

Capabilities

  • Agent that edits files — “Build agents that iteratively search and refine results for complex queries.” source
  • Knows the whole codebase — “Index codebases to power coding agents using AST-aware chunking.” source
  • Command line — “Command-line tools for development” source
  • Choice of models — “Use any embedding model.” source
  • Self-hosted — “Run it locally, self-host, or use Chroma Cloud for a managed, serverless experience.” source
  • API — “Schema() and Search() APIs” source
  • Official SDKs — “Create a self-hosted or cloud database and add data to it using the Chroma SDK.” source
  • Builds agents and workflows — “Build agents that iteratively search and refine results for complex queries.” source
  • Search over your data — “Chroma gives you everything you need for retrieval: store embeddings with metadata, search with dense and sparse vectors, filter by metadata, and retrieve across text, images, and more.” source

Where it works

Web · CLI · API

Security

  • SOC 2 Type II — “Our security program has been independently assessed through a SOC 2 Type II examination, validating the design of our security controls.” source
  • SOC 2 — “Our security program has been independently assessed through a SOC 2 Type II examination, validating the design of our security controls.” source

Alternatives to Chroma

  • Qdrant

    Qdrant stores and searches vector data for semantic, similarity, keyword, and hybrid retrieval in AI applications.

  • Pinecone

    Pinecone is a managed vector database for semantic, keyword, and hybrid search in AI applications.

  • Weaviate

    Weaviate is an open-source vector database for storing and searching data in AI applications, with self-hosted and managed cloud options.

  • Milvus

    Milvus is an open-source vector database for storing embeddings and searching them by similarity, with options for filtering and scaling.

  • Zilliz Cloud

    Managed vector database for storing, indexing, and searching embeddings in AI applications.

  • LangFlow

    Langflow lets developers build, test, and deploy AI workflows, agents, and MCP servers with a visual editor and Python components.

Questions about Chroma

Is Chroma free?

No. The maker’s pricing page lists no free plan for Chroma. Prices checked on 10 Nov 2026.

How much does Chroma cost?

The plans on the maker’s pricing page: Starter ($0/mo), Team ($250/mo) and Enterprise (price on request). Prices checked on 10 Nov 2026.

Does Chroma have an API?

Yes. The maker’s pages state that Chroma has an API. Read on the maker’s pages on 18 Nov 2026.

Which platforms does Chroma run on?

Chroma runs on Web, CLI and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.

Is Chroma open source?

Yes. The code of Chroma is published at github.com/chroma-core/chroma under the Apache-2.0 licence. Read on the maker’s pages on 18 Nov 2026.

Is Chroma still available?

Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that Chroma has ended.

Sources

Not confirmed

Latest version
The product pages read did not identify a current ChromaDB version.
Official website