Google Launches Gemini Embedding Model for Enhanced Text Processing

Jul 25, 2025
Google has introduced the Gemini Embedding model, now available in the Gemini API, offering advanced capabilities for text processing tasks such as Retrieval-Augmented Generation and classification.

Google has launched the Gemini Embedding model, now available in the Gemini API, announced on their website. This model is designed to enhance text processing tasks, including Retrieval-Augmented Generation (RAG), classification, and search.

The Gemini Embedding model is noted for its versatility and power, achieving top scores on the Massive Text Embedding Benchmark (MTEB) leaderboard. It supports over 100 languages and offers a controllable embedding size, priced at $0.15 USD per million tokens.

Users can generate text embeddings using the `embed_content` method, which allows for the creation of embeddings for words, phrases, sentences, and code. These embeddings are crucial for tasks such as semantic search, classification, and clustering, providing more accurate and context-aware results than traditional keyword-based approaches.

For enterprise-grade applications, the model is also available on Vertex AI, offering optimized performance for high-volume workloads. The Gemini Embedding model's introduction marks a significant advancement in Google's AI capabilities, providing developers with powerful tools for a wide range of natural language processing tasks.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.