Catalog Systems Embedding & reranker services Cohere Embed

Cohere Embed

https://cohere.com/embed

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).

Active · Verified 2026-10-28 · fresh as of 2026-10-28 · 23 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Type
Hosted embeddings API vendor fix
Tier
T1
Section
Embedding & reranker services
Created
2021 vendor fix
Latest release
Embed 5 (2026-09-30) vendor fix
License
proprietary; Python SDK MIT registry fix
GitHub
cohere-ai/cohere-python — ~406 stars, last commit 2026-10 (official Python SDK) repo fix
Pricing
Model Vault dedicated instances: Embed 5 Fast/Pro Small $3.00/hour ($2,000/month), Medium $5.00/hour ($3,250/month); Rerank 5 Fast Medium $4.00/hour ($2,500/month); embed models billed per token embedded, rerank per search on the API vendor fix
Funding
Cohere raised $500M Series D 2024-07 ($5.5B valuation; PSP Investments + Cisco led); ~$970M total. vendor fix
Freshness
2026-10-28 fix
Layer
model-infra repo fix
Licensing
commercial registry fix
Deployment locus
hybrid vendor fix
Platform vs product
platform vendor fix
SDK languages
go, java, python, rest, typescript vendor fix
Protocols
openai-compatible vendor fix
Compliance
soc2-type2 vendor fix
Developer activity
OpenRank 1.78 (12-mo avg 4.03) · 10 participants — 2026-09 third-party fix
Maintainer health
10 issues in 90 days, 100% answered or closed · 23 releases in 12 months (latest 2026-10-21) · bus factor 4 — as of 2026-10-31 repo

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

Cohere $500M Series D 2024 at $5.5B; revenue ~$100M ARR (2024).

Technical surface

API surface
REST API (Embed, Rerank endpoints), Python SDK, TypeScript SDK
Backend storage
searched not found
Deployment
Both (self-hosted + managed cloud) — Cohere API and Model Vault; deployable in customer cloud via Amazon SageMaker, Azure AI Foundry and Oracle OCI
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
searched not found
A2A
searched not found
OpenTelemetry
searched not found

Compare Cohere Embed with…

Alternatives to Cohere Embed → 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.

  • 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.

  • Mistral Embed T2

    Mistral AI's hosted embedding API — mistral-embed; available via Mistral La Plateforme and Azure AI.

Sources (22 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; Python SDK MIT” source
    • Latest release first recorded as “Embed 5 (2026-09-30)” source
    • Pricing first recorded as “Model Vault dedicated instances: Embed 5 Fast/Pro Small $3.00/hour ($2,000/month), Medium $5.00/hour ($3,250/month); Rerank 5 Fast Medium $4.00/hour ($2,500/month); embed models billed per token embedded, rerank per search on the API” source
    • Deployment first recorded as “Both (self-hosted + managed cloud) — Cohere API and Model Vault; deployable in customer cloud via Amazon SageMaker, Azure AI Foundry and Oracle OCI” source
    #274

Related systems

References (10)

  • Chroma integrates with — Cohere docs "Integrating Embedding Models with Other Tools": Chroma and Cohere guide. (verified 2026-10-29)
  • Elasticsearch integrates with — Cohere docs "Integrating Embedding Models with Other Tools": Elasticsearch and Cohere guide. (verified 2026-10-29)
  • Haystack (framework) integrates with — Cohere docs "Integrating Embedding Models with Other Tools": Haystack and Cohere guide. (verified 2026-10-29)
  • LangChain (framework) integrates with — Cohere docs "Integrating Embedding Models with Other Tools": LangChain (Cohere Embed on LangChain) and Cohere guide. (verified 2026-10-29)
  • Milvus integrates with — Cohere docs "Integrating Embedding Models with Other Tools": Milvus and Cohere guide. (verified 2026-10-29)
  • MongoDB Atlas Vector Search integrates with — Cohere docs "Integrating Embedding Models with Other Tools": MongoDB and Cohere guide. (verified 2026-10-29)
  • Pinecone integrates with — Cohere docs "Integrating Embedding Models with Other Tools": Pinecone and Cohere guide. (verified 2026-10-29)
  • Qdrant integrates with — Cohere docs "Integrating Embedding Models with Other Tools": Qdrant and Cohere guide. (verified 2026-10-29)
  • Vespa integrates with — Cohere docs "Integrating Embedding Models with Other Tools": Vespa and Cohere guide. (verified 2026-10-29)
  • Weaviate integrates with — Cohere docs "Integrating Embedding Models with Other Tools": Weaviate and Cohere guide. (verified 2026-10-29)

Referenced by (13)

  • Chroma integrates with — Chroma's docs have a Cohere Embed integration page. (verified 2026-10-29)
  • Cohere Command R+ / Command A depends on at runtime — adjacent-infrastructure cell: Cohere Embed v4; Cohere Rerank v3; Oracle Cloud Infrastructure deep integration
  • LanceDB integrates with — LanceDB's docs have a Cohere Embed integration page. (verified 2026-10-29)
  • LangChain (framework) integrates with — LangChain docs have a Cohere embeddings integration page (CohereEmbeddings). (verified 2026-10-29)
  • Langflow integrates with — Langflow components bundle: Cohere Embeddings component. (verified 2026-10-29)
  • LlamaIndex (framework) integrates with — LlamaIndex has an official embeddings integration package llama-index-embeddings-cohere in its repo. (verified 2026-10-29)
  • Milvus integrates with — Milvus's integrations overview lists a Milvus + Cohere Embed integration tutorial. (verified 2026-10-29)
  • n8n (AI agent flows) integrates with — n8n built-in AI cluster node: Embeddings Cohere node. (verified 2026-10-29)
  • NVIDIA NeMo Guardrails integrates with — NeMo Guardrails docs have a Cohere embeddings provider page. (verified 2026-10-29)
  • Phidata (now Agno) integrates with — Agno ships a cohere embedder (agno.knowledge.embedder.cohere). (verified 2026-10-29)
  • Pinecone integrates with — Pinecone's integrations directory has a Cohere Embed integration page. (verified 2026-10-29)
  • Pydantic-AI integrates with — Pydantic AI embeddings docs list Cohere as an embeddings provider. (verified 2026-10-29)
  • Qdrant integrates with — Qdrant's documentation has a Cohere Embed integration page. (verified 2026-10-29)