# EmbeddingGemma 2

> EmbeddingGemma 2 is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimensional vector space. The model has 740M total parameters, combining a 270M parameter text model with modular vision (170M) and audio (300M) encoders. AnyRouter exposes the text path via /embeddings — the OpenAI-compatible body is a text `input`, so the multimodal encoders (text/image/video/audio natively, 8,192-token shared window) are not reachable from this endpoint. Runs on the user's own paired device via Ollama and the AnyRouter relay.

**ID**: `google/embeddinggemma-2`  
**Creator**: Google  
**Category**: embedding  
**Context**: 8K tokens  
**Input**: $0  
**Output**: $0  
**Released**: 2026-10-06  
**Web page**: https://anyrouter.dev/model/google/embeddinggemma-2

**Input modalities**: text  
**Output modalities**: embeddings  

**Tokenizer**: Gemma

**Capabilities**: embedding

**Supported parameters**: input, model, dimensions, encoding_format

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/embeddings`

```bash
curl https://anyrouter.dev/api/v1/embeddings \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/embeddinggemma-2",
  "input": "The quick brown fox jumps over the lazy dog"
}'
```

Pass `input` as a string or an array of strings to embed a batch in one call.

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| ollama-anyr-relay | $0 | $0 |

## Source

- Upstream docs: https://blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2/