Catalog Systems Embedding & reranker services Mixedbread AI

Mixedbread AI

https://www.mixedbread.com/

Agentic search platform that ingests PDFs, decks, video, code, Slack and Drive and returns evidence to agents. Built on its own models and database: Wholembed V3 (late-interaction, omnimodal) embeddings, mxbai-rerank listwise reranker, a trained search agent and Silo, an S3-native multi-vector engine. Earlier open-weight models (mxbai-embed-large, mxbai-rerank) and a paid API.

Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 21 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Type
Embedding + reranker API vendor fix
Tier
T2
Section
Embedding & reranker services
Created
2023 vendor fix
Latest release
v0.78.0 (2026-09-14) — @mixedbread/sdk registry fix
License
proprietary API; open-weight models Apache-2.0 (mxbai-embed-large-v1, mxbai-rerank-v2); SDKs Apache-2.0 registry fix
GitHub
searched not found vendor fix
Pricing
Starter free ($5 one-time credits); Scale $20/month (includes $20 credits, then pay-as-you-go); Enterprise custom. Indexing $1.50/1M tokens (Fast) or $3 (High Quality); semantic search $4 per 1K queries (+$3.50 with rerank); grep search $0.10 per 1K queries vendor fix
Funding
Pre-seed / undisclosed (2024); German embeddings/rerankers startup; OSS-friendly. third-party fix
Freshness
2026-10-29 fix
Layer
model-infra repo fix
Licensing
commercial registry fix
Deployment locus
hybrid vendor fix
Platform vs product
platform vendor fix
SDK languages
python, rest, typescript vendor fix
Protocols
mcp-server vendor fix
Compliance
gdpr, iso27001, soc2-type1, soc2-type2 vendor fix

When to use

Optimised for: searched not found

Anti-fit: searched not found

Pros & cons

Pros

searched not found

Cons

searched not found

Claims & capabilities

mxbai-embed-large widely used as Cohere/OpenAI alternative.

Technical surface

API surface
REST API, Python SDK, TypeScript SDK, CLI, MCP server
Backend storage
searched not found
Deployment
Both (self-hosted + managed cloud) — managed Mixedbread API (BYOC/BYOB on Enterprise); Apache-2.0 open-weight models self-hostable
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
yes — official Mixedbread MCP Server connecting AI assistants to Mixedbread Stores/Search
A2A
searched not found
OpenTelemetry
searched not found

Alternatives to Mixedbread AI → live options ranked by shared design, licence, hosting and MCP support

Similar systems

Other embedding & reranker services in the catalog, ranked by inbound references.

  • Voyage AI (MongoDB) T1

    Specialised embedding and reranker provider — voyage-3, voyage-multilingual, voyage-finance, voyage-law, voyage-code. Acquired by MongoDB Feb 2025 for $220M.

  • Cohere Embed T1

    Cohere's hosted embedding models, now Embed 5 (2026-09-30; Pro and Fast tiers): text, image and fused text-plus-image inputs, 100+ languages, 128K-token context, Matryoshka output dimensions from 256 to 2048 with float, int8 and binary formats. Reranker API (Rerank 5).

  • Jina AI Embeddings T1

    Jina AI's embedding family — jina-embeddings-v3 (multilingual), jina-clip-v2 (text+image), jina-colbert-v2. Open-weights + hosted API + ColBERT-style.

  • OpenAI Embeddings T1

    OpenAI's hosted embedding API — text-embedding-3-small, text-embedding-3-large. Most widely used commercial embedding API in OSS RAG/memory stacks.

  • Hugging Face Inference API (Embeddings) T1

    HF's hosted Inference API and Inference Endpoints — serve any model from the Hub including the BGE/GTE/E5 embedding families.

  • Sentence Transformers T1

    Reimers & Gurevych's library for training sentence embeddings — substrate under most open-weight embedding models. Now under Hugging Face.

Sources (20 cited facts, 1 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-27
    • License first recorded as “proprietary API; open-weight models Apache-2.0 (mxbai-embed-large-v1, mxbai-rerank-v2); SDKs Apache-2.0” source
    • Latest release first recorded as “v0.78.0 (2026-09-14) — @mixedbread/sdk” source
    • Pricing first recorded as “Starter free ($5 one-time credits); Scale $20/month (includes $20 credits, then pay-as-you-go); Enterprise custom. Indexing $1.50/1M tokens (Fast) or $3 (High Quality); semantic search $4 per 1K queries (+$3.50 with rerank); grep search $0.10 per 1K queries” source
    • Deployment first recorded as “Both (self-hosted + managed cloud) — managed Mixedbread API (BYOC/BYOB on Enterprise); Apache-2.0 open-weight models self-hostable” source
    • MCP support first recorded as “yes — official Mixedbread MCP Server connecting AI assistants to Mixedbread Stores/Search” source
    #274

Related systems

Referenced by (4)

  • Haystack (framework) integrates with — Haystack integrations directory has a mixedbread ai integration page ("Use mixedbread's models as well as top open-source models in seconds"). (verified 2026-10-29)
  • LlamaIndex (framework) integrates with — LlamaIndex has an official embeddings integration package llama-index-embeddings-mixedbreadai in its repo. (verified 2026-10-29)
  • Qdrant integrates with — Qdrant's documentation has a Mixedbread AI integration page. (verified 2026-10-29)
  • Vercel AI SDK integrates with — AI SDK docs have a Mixedbread community provider page. (verified 2026-10-29)