Gemini Embedding 2
by Google
First natively multimodal embedding model supporting text, images, video, audio, and documents
Input Price
$0.2
per 1M tokens
Output Price
$0.2
per 1M tokens
Context Window
8.192K
tokens (3.072K max output)
Specifications
Capabilities
Related Use Cases
AI Chatbot
Calculate the API cost of running a customer support or conversational AI chatbot.
Document Summarizer
Calculate how much it costs to summarize documents, reports, and articles with AI.
Content Generation
Calculate the cost of generating blog posts, marketing copy, and articles with AI.
Image Analysis
Calculate the cost of analyzing images with AI vision models.
Data Extraction
Calculate the cost of extracting structured data from unstructured text with AI.
AI Translation
Calculate the cost of translating text with AI language models.
Monthly Cost Estimates
| Usage Level | Daily Tokens | Daily | Monthly | Yearly |
|---|---|---|---|---|
| Light~50 requests/day | 100K in / 20K out | $0.02 | $0.72 | $9 |
| Medium~200 requests/day | 500K in / 100K out | $0.12 | $3.60 | $44 |
| Heavy~1K requests/day | 2,000K in / 500K out | $0.50 | $15.00 | $183 |
| Enterprise~5K requests/day | 10,000K in / 2,000K out | $2.40 | $72.00 | $876 |
Cost Calculator
Alternatives to Gemini Embedding 2
💰 Cheaper Options
Frequently Asked Questions
How much does Gemini Embedding 2 API cost per million tokens?▼
What is the Gemini Embedding 2 context window?▼
How much does Gemini Embedding 2 cost per month?▼
Is there a cheaper alternative to Gemini Embedding 2?▼
Is Gemini Embedding 2 good for ai chatbot?▼
Gemini Embedding 2 Comparisons
Ready to use Gemini Embedding 2?
Get started with Google's API — free tier available for most models.
Related Articles
Gemini Omni Flash and Nano Banana 2 Lite: 6 Creative Workflows Teams Can Ship Now
Google's Gemini Omni Flash and Nano Banana 2 Lite open practical image-to-video workflows for creative teams, agencie...
7/27/2026
Gemini 3.6 Flash Makes Production Agents Cheaper: 7 Workflows to Build Now
Google's Gemini 3.6 Flash and 3.5 Flash-Lite make agent workflows faster and cheaper. See what changed, use cases, ro...
7/22/2026
Ternlight Brings 7 MB Browser-Native Embeddings: 6 Private Search Workflows Builders Can Ship Now
Ternlight is a 7 MB browser embedding model for local RAG and private semantic search. See when it beats hosted APIs,...
7/7/2026