As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/gemini-embedding-2/

# Gemini Embedding 2

Google DeepMind, Gemini Embedding family. Status: current. Type: embedding model. Released: 2026-04-22.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Gemini API | `gemini-embedding-2` | https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent | https://ai.google.dev/gemini-api/docs/embeddings |
| Google Cloud Gemini Enterprise Agent Platform (Vertex AI) |  |  | https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/embedding-2 |

## Pricing

- Input: $0.20 per 1M tokens
- Unit as published: per 1M text input tokens; image $0.45/1M (~$0.00012 per image), audio $6.50/1M (~$0.00016/s), video $12.00/1M (~$0.00079 per frame)
- Source: https://ai.google.dev/gemini-api/docs/pricing
- Last checked: 2026-09-29

## Specs

- Input: text, image, audio, video, pdf
- Output: text
- Context window: 8,192 tokens
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer embedding models in the registry since its release: 3:
  - EmbeddingGemma 2 (2026-10-06) https://postcutoff.com/m/embeddinggemma-2/
  - Cohere Embed 5 Fast (2026-09-30) https://postcutoff.com/m/cohere-embed-v5-fast/
  - Cohere Embed 5 Pro (2026-09-30) https://postcutoff.com/m/cohere-embed-v5-pro/
- After it from Google: EmbeddingGemma 2 (2026-10-06) https://postcutoff.com/m/embeddinggemma-2/
- Closed weights; access is hosted only.

## What stands out

- Natively multimodal embeddings: Text, images, video, audio and PDFs mapped into one embedding space; Google's first natively multimodal embedding model and first in the Gemini API. Source: https://ai.google.dev/gemini-api/docs/embeddings
- Matryoshka dimensions: Flexible 128-3072 output dimensions (recommended 768/1536/3072); 100+ languages. Source: https://ai.google.dev/gemini-api/docs/embeddings

## Notes

Public preview March 2026 (id gemini-embedding-2-preview, still listed), GA 2026-04-22. modality_out 'text' is a placeholder: output is a vector. Predecessor gemini-embedding-001 (text-only) shuts down 2028-05-14.

Embeddings for multimodal RAG, semantic search, clustering and classification.

```python
from google import genai
client = genai.Client()
r = client.models.embed_content(model="gemini-embedding-2", contents="What is the meaning of life?")
```

Sources: [embeddings guide](https://ai.google.dev/gemini-api/docs/embeddings), [pricing](https://ai.google.dev/gemini-api/docs/pricing), [deprecations](https://ai.google.dev/gemini-api/docs/deprecations), [launch blog](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-embedding-2/).

Model page: https://postcutoff.com/m/gemini-embedding-2/