# Gemini Embedding 2

> Gemini Embedding 2 is a proprietary language model from Google DeepMind, released on 22 Apr 2026. It accepts text, images, audio, video and PDFs and generates text, with a 8K-token context window and up to 1 output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.20 per million input tokens and Free per million output tokens (Gemini API), across 2 providers we track.

Source page: https://www.aimodel.directory/models/gemini-embedding-2
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Google DeepMind
- **Release date:** 22 Apr 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-embedding-2.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-embedding-2.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-embedding-2.toml)
- **Context window:** 8K (8,192 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-embedding-2.toml)
- **Max output:** 1 tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-embedding-2.toml)
- **Knowledge cutoff:** Nov 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-embedding-2.toml)
- **Input:** Text, images, audio, video and PDFs (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-embedding-2.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-embedding-2.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-embedding-2.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/google/models/gemini-embedding-2.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Gemini API | $0.20 | Free | – | 8K |
| Vercel AI Gateway | – | – | – | – |

## FAQ

### What is the context window of Gemini Embedding 2?

Gemini Embedding 2 has a context window of 8,192 tokens (8K) and can generate up to 1 tokens in a single response, according to models.dev.

### How much does the Gemini Embedding 2 API cost?

Through Gemini API, Gemini Embedding 2 costs $0.20 per million input tokens and Free per million output tokens. Prices last verified 4 Oct 2026.

### Is Gemini Embedding 2 open source?

No. Gemini Embedding 2 is a proprietary model; Google DeepMind has not released its weights. It is available through APIs including Gemini API, Vercel AI Gateway.

### When was Gemini Embedding 2 released?

Google DeepMind released Gemini Embedding 2 on 22 Apr 2026, according to models.dev.

### Which providers offer Gemini Embedding 2?

We track Gemini Embedding 2 on 2 providers: Gemini API, Vercel AI Gateway.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Gemini Embedding 2", https://www.aimodel.directory/models/gemini-embedding-2