Best forMultilingual search with embeddings and a reranker from the same vendor.
Trade-offFree trial keys are rate-limited and not for commercial use.
Used by 19 makers' products for this
For embeddings, the alternatives to Voyage AI that makers' products we track chose most are Cohere (19). 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 | 0 | — | No | ||
| Retrieval specialist | 19 | — | No | ||
| General LLM provider | 0 | No | 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.
Voyage AI (Retrieval specialist): Retrieval quality on specialized text, with models tuned for code, legal and finance documents. Trade-off: Hosted API apart from one small open-weight model; now run by MongoDB, so its roadmap follows MongoDB's.
Best forMultilingual search with embeddings and a reranker from the same vendor.
Trade-offFree trial keys are rate-limited and not for commercial use.
Used by 19 makers' products for this
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 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
It depends on what you need it for; we don't rank them. The one makers' products we track chose most for embeddings is Cohere (19 makers' products). You already use OpenAI or Gemini for text and want no new vendor: OpenAI API and Gemini API. Your users search in many languages, or you want embeddings and a reranker from one API: Cohere and Jina AI. Text must not leave your servers, or embedding volume makes per-token pricing add up: Sentence Transformers.
Yes. For embeddings, Gemini API has a free tier a small product can start on.
Yes. For embeddings: Sentence Transformers.