Updated

Cohere

API platform for large language models, text embeddings, reranking, and enterprise search/agent tools.

19 makers' products we track use Cohere. 58 open-source projects also declare it in their code.

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use Cohere

Makers' products we track use Cohere for embeddings (19), most often alongside OpenAI API (63%), Vercel (58%), Stripe (58%).

What Cohere is used for

Embeddings · Retrieval specialist →Multilingual search with embeddings and a reranker from the same vendor.Trade-off: Free trial keys are rate-limited and not for commercial use.
Cohere19OpenAI API0Voyage AI0Jina AI0Gemini API0Makers' products on each, for embeddings

Often paired with

Share of the 19 makers' products on Cohere that show this choice.

Markets that build with it most

Product Hunt markets where Cohere is in far more of the stacks we know than across every market (0%).

When to use Cohere, and when not

Pick Cohere if

  • Your users search in many languages, or you want embeddings and a reranker from one API. Embeddings →

Something else fits better if

  • You already use OpenAI or Gemini for text and want no new vendor: OpenAI API or Gemini API.
  • Generic embeddings miss the terms in your code, legal or finance documents: Voyage AI.
  • Text must not leave your servers, or embedding volume makes per-token pricing add up: Sentence Transformers.
From each decision's guide, written from what makers' products chose and why.

How Cohere itself is built

6 tools, from its own code, website and Product Hunt page.

Who uses it

19 makers' products, each linked to the source that shows it, and 58 open-source projects that declare it in their code. The best known on Product Hunt: Brew (1,808 followers), CustomGPT (1,517 followers), Macaly (1,482 followers), Slashspace AI (1,038 followers), Tyce (980 followers).

The maker says so 12Subprocessor list 8Declared in code 58How evidence is collected →
Liveblocks
LiveblocksHosted realtime infrastructure for multiplayer features like presence, comments, notific…

“We used Cohere as it was a cost-effective document indexing solution that provided efficient embedding generation for knowledge base features.”

EmbeddingsMaker says so +1 · source ↗
Meilisearch
MeilisearchFast, typo-tolerant open-source search engine with hybrid full-text and vector search, s…

“We use Cohere 3.5 reranker for our personalization feature”

EmbeddingsMaker says so · source ↗
Officely AI
Officely AIAny Process to AI with All LLM Models

“We use Cohere as an endpoint in our team builder flow; you can combine this model with all available models.”

EmbeddingsMaker says so · source ↗
CustomGPT
CustomGPTBuilds AI chatbots trained on a business's own content, used for customer support and ot…

“We used Cohere multi-modal embeddings to select the images for the articles. We found that this works better than GPT-Vision to select high-quality images that are contextually relevant to the surrounding text. This was a hard problem to solve, and Cohere's multi-modal embedding quality helped improve the quality of the selected images.”

EmbeddingsMaker says so · source ↗
Agora
AgoraShop for millions of e-commerce products with AI

“We are blown away by Cohere Embed 4’s ability to accurately surface relevant products to search queries. E-commerce data is complex, containing images and multifaceted text descriptions. Being able to represent our products in a unified embedding makes our search faster and our internal tooling more efficient.”

EmbeddingsMaker says so · source ↗
Channel3
Channel3API to find any product and earn commission on sales

“Embed V4 is the smartest multimodal embedding model on the market.”

EmbeddingsMaker says so · source ↗

Open source: a project that declares Cohere as a dependency in its public code — verifiable, but not necessarily a live product.

What its projects tell coding agents

18 of the 33 open-source products built with Cohere that were worked on in the last 180 days keep instruction files for coding agents — 55%, against 53% of all the projects we read. AGENTS.md is in 16, CLAUDE.md in 8.

768words in the median file
npmthe package manager most named, in 5 of 17 files
76%say how to test a change
Named more in these files than in other projects' — in how many of the 17:
What AGENTS.md files say about other tools →What open-source products tell their coding agents →

Alternatives to Cohere

All alternatives by situation →

Questions makers ask about Cohere

Is Cohere good for production?

19 makers' products we track run on it.

What is Cohere used for?

API platform for large language models, text embeddings, reranking, and enterprise search/agent tools. Makers' products we track use it for embeddings (19).

When should you use Cohere?

Your users search in many languages, or you want embeddings and a reranker from one API (embeddings). Something else fits better if: you already use OpenAI or Gemini for text and want no new vendor, pick OpenAI API or Gemini API; Generic embeddings miss the terms in your code, legal or finance documents, pick Voyage AI.

Is Cohere open source or self-hostable?

Not open source, and hosted only.

Can AI coding agents work with Cohere?

No llms.txt, official MCP server or CLI found yet.

Who uses Cohere?

19 makers' products we track, each with a source, and 58 open-source projects declare it in their code. The best known of them on Product Hunt: Brew (1,808 followers), CustomGPT (1,517 followers), Macaly (1,482 followers), Slashspace AI (1,038 followers), Tyce (980 followers). source ↗