Embeddings model
gemini-embedding-2-preview pricing
Google Gemini charges $0.20 per million input tokens to embed with gemini-embedding-2-preview, or $0.10 through the Batch API. Below: what common indexing and search workloads cost.
- Input
- $0.20/ 1M
- Audio input
- $6.50/ 1M
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.20 | $0.00 | — | — |
| Batch | $0.10 | — | — | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Cost | |
|---|---|---|
| Embed a 10,000-document corpus | 500 tokens per document | $1.00 |
| Embed 1M search queries | 20 tokens per query | $4.00 |
Planning a mix of models? Simulate a workload with gemini-embedding-2-preview, alongside anything else you run.
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Google Gemini pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.