# Gemini Embedding 2 Usage, Cost & Rank | OpenCode Data

> Gemini Embedding 2 costs $0.20 per 1M input tokens and $0.00 per 1M output tokens.

Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space

- Page: https://opencode.ai/data/google/gemini-embedding-2
- JSON: https://opencode.ai/data/google/gemini-embedding-2.json
- Model ID: google/gemini-embedding-2
- Lab: Google

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 8.2K |
| Max output | 3.1K |
| Knowledge cutoff | 2025-11 |
| Release date | 2026-04-22 |
| Input modalities | text, image, audio, video, pdf |
| Output modalities | text |
| Reasoning | No |
| Tool calling | No |
| Open weights | No |

## Pricing: USD per 1M tokens

| Input | Output | Cached input | Cache write |
| --- | --- | --- | --- |
| $0.20 | $0.00 | - | - |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.