Model detail
Gemini Embedding 2 preview model
Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports input context up to 8,192 tokens and flexible output dimensions from 128 to 3,072 (recommended: 768, 1536, or 3,072). Designed for cross-modal similarity — you can embed a text query and retrieve the most relevant images, or vice versa — making it well-suited for multimodal search, recommendation, and document understanding pipelines.
Model specs
- Model ID
-
gemini-embedding-2-preview
- Context length
- –
- Max output
- –
- I/O modalities
- Released
- 2026-04
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
Gemini
/v1beta/models/{model}:generateContentPOST -
OpenAI-compatible
/v1/chat/completionsPOST
03
Pricing
Flat rate, unit: /1M Tokens
Input
$0.2000 /1M Tokens
Completion
$0.8000 /1M Tokens
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
Gemini Embedding 2 Preview is Google's first multimodal embedding model
Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG).
What should you check before using it?
Confirm vector dimensions and token limits
Model type: embedding. Verify supported features and quotas with the provider documentation. Released 2026-03-10.
Why use it through MixRoute?
Gemini Embedding 2 preview model takes text and images on one route
Text and image inputs share the same route and the same key. MixRoute serves Gemini Embedding 2 preview model on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID gemini-embedding-2-preview and re-run your integration tests.
07
Capabilities & compatibility
Unconfirmed capabilities stay "Unknown," no guesses
Vision input
Gemini Embedding 2 preview model can process image inputs alongside text.
image_url content part alongside text messages.
OpenAI SDK
Call Gemini Embedding 2 preview model through MixRoute's OpenAI-compatible endpoint.
base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.
08
Token cost estimator
Live estimate from this page's pricing, not an actual bill
This model has no cache-read price; caching is not counted
09
FAQ
Yes. Gemini Embedding 2 preview model is reachable through an OpenAI-compatible endpoint, so an existing OpenAI SDK client works after pointing the base URL at MixRoute and setting the model parameter to gemini-embedding-2-preview. Keep your current request and response handling.
One endpoint, a testable decision
Test this model and alternate routes with the same request format
Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.