Google is officially rolling out its Gemini Embedding model, called the gemini-embedding-001, to all developers via the Gemini API and Vertex AI. It was first launched experimentally in March, and this embedding model has already earned a top spot on the Massive Text Embedding Benchmark (MTEB) Multilingual leaderboard. It also outperformed both Google’s earlier models and other commercial offerings in tasks such as classification, search, and retrieval.
Now, with general availability, developers will be able to integrate Gemini Embedding into their applications at no cost or scale up with paid options starting at $0.15 per million input tokens.
If we talk about Gemini Embedding, then it supports over 100 languages and handles input lengths up to 2048 tokens, making it well-suited for global applications. It also brings flexibility with Matryoshka Representation Learning (MRL). This means that it allows developers to choose between different output dimensions (768, 1536, or 3072), depending on their performance and cost requirements.
Importantly, the model isn’t limited to any single domain. Google says it performs well across industries such as science, legal, finance, and software development, offering a more unified embedding solution for various enterprise and research use cases.
Developers Are Encouraged to Migrate
For those using older or experimental models like gemini-embedding-exp-03-07, embedding-001, or text-embedding-004, Google has laid out a timeline for deprecation, with the first cutoff hitting August 14, 2025. Developers are encouraged to migrate to gemini-embedding-001 sooner.
Gemini Embedding is available via the embed_content endpoint in the Gemini API, and Google has shared sample Python code and updated documentation to help teams get started quickly.
Apart from that, Google has teased that support for asynchronous batch processing is coming soon, promising lower-cost, high-volume embedding options for enterprise use cases.
Like what you just read? We share more stories like this on WhatsApp. Join now!
