Skip to main content
Google Gemini

Gemini Embedding 2 pricing, context window and limits

Gemini Embedding 2 costs $0.2 per million input tokens and $0 per million output tokens at Google Gemini list price. It accepts up to 8,192 tokens of context and returns up to 1 tokens.

  • Model id gemini-embedding-2
  • Snapshot

What does Gemini Embedding 2 cost?​

List prices in US dollars per million tokens
Input$0.2
Output$0
Cached input (read)—
Cache write—

US dollars per million tokens. A dash means no price is published.

How much can Gemini Embedding 2 read and write?​

Token limits
Context window8,192
Max output1

What can Gemini Embedding 2 do?​

Capabilities
Vision (image input)Yes
Tool callingNo
Structured outputNo
ReasoningNo
Inputtext, image, audio, video, pdf
Outputtext

What does a request to Gemini Embedding 2 cost?​

Cost of example requests at list price, in US dollars
A typical request: 1,000 tokens in, 500 out$0.0002
A long request: 10,000 tokens in, 1,000 out$0.002
1,000 typical requests$0.2
1 million tokens in and 1 million out$0.2

Among 35 Google Gemini models with a published price, Gemini Embedding 2 is the 5th cheapest by input price. Its context window is the 33rd largest of 40. List prices only; discounts, batch prices and prices above 200K tokens are not shown.

How do I call Gemini Embedding 2 through DVARA?​

Configure the gemini provider in the DVARA LLM Gateway and send the model id gemini-embedding-2. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.

In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.

What should I check before relying on this data?​

The weekly review marked this entry. A person saw each mark and kept the model listed.

  • Output is listed cheaper than input, which is unusual.
  • This provider bills prompt caching, but no cached-input price is listed.

Which other Google Gemini models are there?​

All 40 Google Gemini models · Search the full catalogue

Which models from other providers are similar to Gemini Embedding 2?​

These are the closest in context window and input price, one per provider.

Snapshot 16 October 2026. DVARA reviews every price weekly before it is published. Get the whole catalogue as llm-models.json. Prices are list prices in US dollars per million tokens; check your provider contract before you budget.