Gemini Embedding 2: API pricing, providers and specs
Gemini Embedding 2 is a embedding model by Google. 5 providers serve it, from $0.20 to $0.20 /1M; the lowest price is at APIYI.
How Gemini Embedding 2 compares
Against the 15 embedding models on the site priced the same way.
- Pricey for its class: at $0.20 /1M, its lowest price is above 81% of comparable models (median $0.059).
- Its 8K-token context window is larger than 11% of them (median 8K), about 10 pages of text.
- 5 providers serve it; 63% of comparable models have fewer.
Gemini Embedding 2 prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 AIHubMix | $0.20/1M | Free/1M | — | — |
| ZenMux | $0.20/1M | Free/1M | — | 8K |
| DevPass (LLM Gateway) | $0.20/1M | FromFree/1M | — | — |
 Impossibl | $0.20/1M | Free/1M | — | — |
 APIYI | $0.20/1M | $0.20/1M | — | — |
Specs
- Type
- Embedding
- Maker
- Inputs
- Audio, Image, Text, Video
- Outputs
- Text
- Context
- 8K≈ 10 pages of text
- Max output
- —
- Capabilities
- Vision
- Released
- Mar 10, 2026
- License
- proprietary
- Open weights
- No, API only
Alternatives to Gemini Embedding 2
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Gemini Embedding 2this model | $0.20/1M | 8K | — | 5 |
 Qwen3-VL Embedding 8B | $0.097/1M | 8K | — | 3 |
 Doubao Embedding Large Text | $0.10/1M | — | — | 1 |
| Text Embedding 3 Large | $0.104/1M | 8K | — | 13 |
| Text Embedding Ada 002 | $0.08/1M | 8K | — | 9 |
More from Google
Gemini 4 ArgonGoogle$8/1MNano Banana 2Google$0.067/imgVeo-3Google$2.50/runNano Banana Pro PreviewGoogle$0.09/runGemini Omni 1.1Google$0.05/secNano Banana 2.1Google$6/1MGemini 3 FlashGoogle$2.40/1MVeo 3.1Google$0.16/secGemini Embedding 2 FAQ
The lowest price for Gemini Embedding 2 is $0.20 /1M, at APIYI.
APIYI, at $0.20 /1M. 5 providers serve Gemini Embedding 2; the table above lists every one with its price.
Gemini Embedding 2 reads up to 8K tokens per request.
No. Gemini Embedding 2 is only available through an API; Google does not publish its weights.
5 API providers serve Gemini Embedding 2. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us