Gemini Embedding 2 Preview vs Voyage 4 Lite

A side-by-side comparison of Gemini Embedding 2 Preview and Voyage 4 Lite: input/output pricing, capabilities and available endpoints, served live from OpenCrow. Both are reachable with the same API key.

Pricing comparison

ItemGemini Embedding 2 PreviewVoyage 4 Lite
Input (per 1M tokens)$0.15$0.02

Specifications

ItemGemini Embedding 2 PreviewVoyage 4 Lite
Context window8,19232,000
Max output8,192—

Capability comparison

ItemGemini Embedding 2 PreviewVoyage 4 Lite
multimodalYes—

Which should you pick

Which has the larger context window, Gemini Embedding 2 Preview or Voyage 4 Lite?

Voyage 4 Lite does — Gemini Embedding 2 Preview accepts 8,192 input tokens and Voyage 4 Lite accepts 32,000.

What can Gemini Embedding 2 Preview do that Voyage 4 Lite cannot?

only Gemini Embedding 2 Preview supports multimodal.

Can I switch between Gemini Embedding 2 Preview and Voyage 4 Lite without changing my code?

Yes. Both are available on OpenCrow through one API key and the same OpenAI-compatible endpoint — switching means changing the model field from "gemini-embedding-2-preview" to "voyage-4-lite", nothing else.

Both are available on OpenCrow under one API key — switching between them means changing the model field and nothing else, so you can use each where it fits rather than picking one.

Gemini Embedding 2 Preview · Voyage 4 Lite · All models