Model prices / Google / Gemini Embedding 2
Gemini Embedding 2
Google · released 2026-04-22
The official API price of Gemini Embedding 2 is $0.2 per 1M input tokens and $0 per 1M output tokens (as of 2026-11-12). Context window: 8.2K tokens, up to 1 output tokens per request. 5 providers sell it, none below the official price.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| GoogleOfficialgemini-embedding-2 | $0.2 | $0 | — | Official | Official docs |
MMerge Gatewaygoogle/ | $0.2 | $0 | — | Official docs | |
TTempr Gatewaygoogle/ | $0.2 | $0 | — | Official docs | |
SSAP AI Coregemini-embedding-2 | — | — | — | Official docs | |
 Vercel AI Gatewaygoogle/ | — | — | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space
Description from models.dev.
Specs
- Type
- Embedding
- Context
- 8.2K
- Max output
- 1
- Input
- Text, Image, Audio, Video, PDF
- Output
- Text
- Reasoning
- No
- Tool calling
- No
- Structured output
- No
- Knowledge cutoff
- 2025-11
- Open weights
- No
- Released
- 2026-04-22
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.