# Gemini Embedding 2

> Google's multimodal embedding model with flexible 128–3072-dim vectors for semantic search, retrieval, and recommendation.

Agent resources: the index of everything machine-readable is https://www.ohmygpt.com/llms.txt; the integration skill (endpoints, auth, SDK and coding-tool setup) is https://www.ohmygpt.com/skill.md.

- Model ID: `google/gemini-embedding-2`
- Status: available
- Released: 2026-04-22
- Context: 8K tokens
- Input: text; output: —

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| Embedding input | $0.22 | per 1M tokens |

## Providers

Without a prefix each request goes to the best-priced healthy provider. To pin one, send the model as `<provider>:google/gemini-embedding-2`.

| Provider | Pinned model ID | Location | Input | Output | Trains on your data |
| --- | --- | --- | --- | --- | --- |
| Google (Gemini) | `google:google/gemini-embedding-2` | United States | — | — | no |

Web page: https://www.ohmygpt.com/models/google/gemini-embedding-2