Best forApps already on the OpenAI API that want solid embeddings with no new vendor.
Trade-offGeneral-purpose models, with no reranking endpoint to pair them with.
No maker product tracked for this yet
1 of the 5 is open source or self-hostable (Sentence Transformers) and 1 has a free tier.
Not a ranking: each option is described by the situation it fits, with its trade-off.
How many makers' products we track use each for embeddings.
| Option | Kind | Makers' products | Free tier | Open source | |
|---|---|---|---|---|---|
| Retrieval specialist | 19 | — | No | ||
| General LLM provider | 0 | No | No | ||
| Retrieval specialist | 0 | — | No | ||
| Retrieval specialist | 0 | — | No | ||
| General LLM provider | 0 | Yes | No | ||
| Open model you run | 0 | — | Yes |
Stay with the vendor you already use, pick a retrieval specialist, or run an open model yourself. Using your main LLM provider's embeddings means one key and one bill. Specialists offer models tuned for retrieval, many languages or specific domains, plus rerankers, at the cost of one more vendor. Open embedding models run on your own hardware for free and keep text private, but you host and scale them.
Cohere (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.
Best forApps already on the OpenAI API that want solid embeddings with no new vendor.
Trade-offGeneral-purpose models, with no reranking endpoint to pair them with.
No maker product tracked for this yet
Best forRetrieval quality on specialized text, with models tuned for code, legal and finance documents.
Trade-offHosted API apart from one small open-weight model; now run by MongoDB, so its roadmap follows MongoDB's.
No maker product tracked for this yet
Best forMultilingual and long-document embeddings you can try without an API key.
Trade-offKeyless use is rate-limited; now part of Elastic, so the product direction may shift.
No maker product tracked for this yet
Best forApps on the Gemini API that want multilingual text embeddings on the same key.
Trade-offGeneral-purpose models, and like any hosted embedding, switching later means re-embedding everything.
No maker product tracked for this yet
Best forRunning open embedding and reranker models on your own CPU or GPU, with thousands of models on the Hugging Face Hub to choose from.
Trade-offPython only; you host, batch and scale the model yourself, and CPU-only servers embed slowly.
No maker product tracked for this yet
Yes. For embeddings, Gemini API has a free tier a small product can start on.
Yes. For embeddings: Sentence Transformers.