Back to models
Gemini Embedding 001 vs Gemini Embedding 2
Gemini Embedding 001 and Gemini Embedding 2: current price, context, max output, and supported operations.
Pricing comparison
| Gemini Embedding 001 | Gemini Embedding 2 | |
|---|---|---|
| Model maker | ||
| Delivery availability | Available | Available |
| Context window | 2K | 8K |
| Max output | - | - |
| Official price | Input$0.15per 1M tokensOutput$0.00per 1M tokens | Input$0.20per 1M tokensOutput$0.00per 1M tokens |
| TokenLab price | Input$0.075per 1M tokensOutput$0.00per 1M tokens | — |
| Model performance | Collecting data | Collecting data |
| Capabilities |
Summary
- Gemini Embedding 001: Input $0.075 / Output $0.00 per 1M tokens; Gemini Embedding 2: Input $0.10 / Output $0.00 per 1M tokens.
- Gemini Embedding 2 has a 4.0x larger context window
FAQ
Which is cheaper, Gemini Embedding 001 or Gemini Embedding 2?
Gemini Embedding 001: Input $0.075 / Output $0.00 per 1M tokens; Gemini Embedding 2: Input $0.10 / Output $0.00 per 1M tokens.
What are the key differences between Gemini Embedding 001 and Gemini Embedding 2?
Both models share similar capabilities.