最新报道:According to the Google Developers Blog, the Gemini Embedding text model (gemini-embedding-001) is now officially open to developers through the Gemini API and Vertex AI. The model supports more than 100 languages, with a maximum input length of 2048 tokens, and uses Matryoshka Representation Learning technology to support multiple output dimension options. Gemini Embedding has performed well on the MTEB multi-language list, covering fields such as science, law, finance, and programming. The model is priced at $0.15 per million input tokens, and developers can try it for free through Google AI Studio.