Embedding models

Developer documentation

Vector generation for semantic search, RAG, retrieval, clustering, ranking, and analytics.

Model Reference

Vector generation for semantic search, RAG, retrieval, clustering, ranking, and analytics. Endpoint: https://omixa.cloud/api/v1/embeddings

embedding-001

Embedding 001 for semantic search, retrieval, ranking, and vector analytics.

Embedding Context window: 2,048 tokens

Input per 1m tokens $0.150000

Minimum hold $0.010000

gemini-embedding-001

Gemini Embedding for semantic search, retrieval, ranking, and vector analytics.

Embedding Context window: 8,192 tokens

Input per 1m tokens $0.150000

Minimum hold $0.010000

gemini-embedding-2

Gemini Embedding 2 for semantic search, retrieval, ranking, and vector analytics.

Embedding Context window: 8,192 tokens

Input per 1m tokens $0.200000

Minimum hold $0.010000

text-embedding-004

Text Embedding 004 for semantic search, retrieval, ranking, and vector analytics.

Embedding Context window: 2,048 tokens

Input per 1m tokens $0.150000

Minimum hold $0.010000

text-embedding-3-large

Text Embedding 3 Large for semantic search, retrieval, ranking, and vector analytics.

Embedding Context window: 8,191 tokens

Input per 1m tokens $0.143000

Minimum hold $0.010000

text-embedding-3-small

Text Embedding 3 Small for semantic search, retrieval, ranking, and vector analytics.

Embedding Context window: 8,191 tokens

Input per 1m tokens $0.022000

Minimum hold $0.010000