Gemini Embedding vs Voyage AI embeddings and rerankers

Gemini Embedding

Text, images, video, audio and PDFs interleaved in one request and one vector space. $0.20 per million text tokens, against $0.02 for OpenAI's small model.

Voyage AI embeddings and rerankers

200 million free tokens per current model, then $0.02 to $0.12 per million. Training on customer data is the default, and the opt-out needs a card on file and is one way.

Gemini Embedding

1. Don't send task_type to gemini-embedding-2. Prefix the text instead, task: search result | query: ... for queries and title: ... | text: ... for documents
2. Ask for output_dimensionality 768 unless you need 3072. Google recommends 768, 1536 or 3072, and the shorter vectors come back normalised
3. Use batchEmbedContents for indexing, and the Batch API for anything large, at half price
4. Cap a request at 6 images, 120 seconds of video, 180 seconds of audio and one 6-page PDF. Split longer media first
5. Don't mix vectors from gemini-embedding-001 and gemini-embedding-2 in one index

Voyage AI embeddings and rerankers

1. Opt the organisation out of training before sending anything private. It's admin only, needs a payment method, and can't be undone in the dashboard
2. Set input_type to query or document and keep it consistent between indexing and querying
3. Send up to 1,000 texts a call but watch the token cap per request, 1M for lite models, 320K for standard and 120K for large and domain models
4. Ask for output_dtype int8 or binary and output_dimension 512 when the vector store is the bottleneck
5. Use rerank-3-lite over the top 100 from a cheap first pass, at $0.02 per million tokens