# EmbeddingGemma 300M

> EmbeddingGemma is a 300M parameter open embedding model from Google, built from Gemma 3 research. Produces text vectors for search, retrieval, classification, clustering, and semantic similarity across 100+ languages.

**ID**: `google/embeddinggemma-300m`  
**Creator**: Google  
**Category**: embedding  
**Context**: 2K tokens  
**Status**: Disabled (since 2026-08-12) — no longer routable or listed; kept for history/usage reference.  
**Reason**: Smoke reported model_unavailable (no upstream for platform keys). See #1799/#1806.  
**Input**: $0.01/M  
**Output**: $0  
**Released**: 2025-09-04  
**Web page**: https://anyrouter.dev/model/google/embeddinggemma-300m

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

**Tokenizer**: Gemma

**Capabilities**: embedding

**Supported parameters**: input, model, 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-300m",
  "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 |
| --- | --- | --- |
| Cloudflare AI Workers | $0.01/M | $0 |

## Source

- Upstream docs: https://developers.cloudflare.com/workers-ai/models/embeddinggemma-300m/