Google introduces new Gemini text embedding model to developers.
Google introduced a new, experimental addition called Gemini Embedding, an "embedding" model for text, to its Gemini developer API on Friday.
Embedding models convert textual inputs—such as words and phrases—into numerical representations, or embeddings, that encapsulate the semantic meaning of the content. These embeddings are used in various applications, including document retrieval and classification, partly because they can lower costs and improve response speed.
Amazon, Cohere, and OpenAI are among the companies that provide embedding models via their own APIs. While Google has offered embedding models in the past, Gemini Embedding is the first one trained using the Gemini family of AI models.
"Trained on the Gemini model itself, this embedding model has inherited Gemini's grasp of language and nuanced context, making it suitable for a wide array of applications," Google stated in a blog post. "We trained our model to be highly general-purpose, delivering outstanding performance across diverse fields like finance, science, law, search, and more."
According to Google, Gemini Embedding outperforms its previous top-tier model, text-embedding-004, and shows competitive results on widely-used embedding benchmarks. Unlike its predecessor, Gemini Embedding can process larger chunks of text and code in a single input and supports over 100 languages—twice as many as before.
Google notes that Gemini Embedding is currently in an "experimental phase" with limited capacity and is subject to future changes. "We plan to move toward a stable, generally available release in the coming months," the company wrote in its blog post.
Related article
Google AI Overviews Gain Ground in Search Results
According to Similarweb’s 2026 Generative AI Landscape report, Google’s AI-generated summaries appeared in 43% of US searches, a significant rise from 15% recorded a year prior.While AI Overviews present generated summaries within standard search res
Google to Pay SpaceX $920M Monthly for Compute
SpaceX has secured another major compute agreement ahead of its landmark IPO, this time partnering with Google. The company disclosed the arrangement in a regulatory filing on Friday.According to the agreement, Google will pay SpaceX $920 million mon
Google expands AI Mode to track flight prices and book hotels
Google has introduced new capabilities within AI Mode, its conversational search interface, allowing users to plan and book trips more effectively, the company revealed on Thursday. The updated features enable users to inquire about flight price tren
Related Special Topic Recommendations
Comments (1)
0/500
Google introduced a new, experimental addition called Gemini Embedding, an "embedding" model for text, to its Gemini developer API on Friday.
Embedding models convert textual inputs—such as words and phrases—into numerical representations, or embeddings, that encapsulate the semantic meaning of the content. These embeddings are used in various applications, including document retrieval and classification, partly because they can lower costs and improve response speed.
Amazon, Cohere, and OpenAI are among the companies that provide embedding models via their own APIs. While Google has offered embedding models in the past, Gemini Embedding is the first one trained using the Gemini family of AI models.
"Trained on the Gemini model itself, this embedding model has inherited Gemini's grasp of language and nuanced context, making it suitable for a wide array of applications," Google stated in a blog post. "We trained our model to be highly general-purpose, delivering outstanding performance across diverse fields like finance, science, law, search, and more."
According to Google, Gemini Embedding outperforms its previous top-tier model, text-embedding-004, and shows competitive results on widely-used embedding benchmarks. Unlike its predecessor, Gemini Embedding can process larger chunks of text and code in a single input and supports over 100 languages—twice as many as before.
Google notes that Gemini Embedding is currently in an "experimental phase" with limited capacity and is subject to future changes. "We plan to move toward a stable, generally available release in the coming months," the company wrote in its blog post.
Google AI Overviews Gain Ground in Search Results
According to Similarweb’s 2026 Generative AI Landscape report, Google’s AI-generated summaries appeared in 43% of US searches, a significant rise from 15% recorded a year prior.While AI Overviews present generated summaries within standard search res
Google to Pay SpaceX $920M Monthly for Compute
SpaceX has secured another major compute agreement ahead of its landmark IPO, this time partnering with Google. The company disclosed the arrangement in a regulatory filing on Friday.According to the agreement, Google will pay SpaceX $920 million mon
Google expands AI Mode to track flight prices and book hotels
Google has introduced new capabilities within AI Mode, its conversational search interface, allowing users to plan and book trips more effectively, the company revealed on Thursday. The updated features enable users to inquire about flight price tren





Home






