General-purpose text embeddings for semantic search, RAG, clustering and dedup. 1536 dimensions (truncatable), cheap, and within pgvector's 2000-dim index limit as-is — the default choice.
Pass species_name to pin this model; omit it and Fire uses the default for the
endpoint. Every response carries meta.price.usd and meta.call_id.
In: text · Out: vector
Family openai · genus text-embedding · served by edenai
Free to sign up. Pay only when you top up.