Back
GoogleGemini API
gemini-pro: New text model for a wide variety of tasks. Balances capability and efficiency
AI summary
Written by AI from the official notes. Check them for exact details.Google released new models including gemini-pro for text tasks and gemini-pro-vision for multimodal tasks.
- gemini-pro: New text model for various tasks.
- gemini-pro-vision: New multimodal model for diverse tasks.
- New embeddings model: embedding-001.
- New AQA model for answering questions with text passages.
- Unified endpoint
GenerateContentfor chat and text.
Why it matters: Users seeking advanced AI capabilities for text and multimodal tasks should explore these new models.
Full release notes39 changes
- gemini-pro: New text model for a wide variety of tasks. Balances capability and efficiency.
- gemini-pro-vision: New multimodal model for a wide variety of tasks. Balances capability and efficiency.
- embedding-001: New embeddings model.
- aqa: A new specially tuned model that is trained to answer questions using text passages for grounding generated answers.
- v1: The stable API channel.
- v1beta: Beta channel. This channel has features that may be under development.
GenerateContentis a single unified endpoint for chat and text.- Streaming available through the
StreamGenerateContentmethod. - Multimodal capability: Image is a new supported modality
- New beta features: Function Calling
- Attributed Question Answering (AQA)
- Updated candidate count: Gemini models only return 1 candidate.
- Different Safety Settings and SafetyRating categories. See safety settings for more details.
- Tuning models is not yet supported for Gemini models (Work in progress).
- Terms
- Privacy
- Manage cookies
- English
- Deutsch
- Español – América Latina
- Français
- Indonesia
- Italiano
- Polski
- Português – Brasil
- Shqip
- Tiếng Việt
- Türkçe
- Русский
- עברית
- العربيّة
- فارسی
- हिंदी
- বাংলা
- ภาษาไทย
- 中文 – 简体
- 中文 – 繁體
- 日本語
- 한국어