Technology
Connecting to the Gemini API via a Single Access
how to leverage the unique strengths of Gemini API frontier models without drowning in SDK maintenance.
A
AnnaCometAPI Blog
One API. Every Leading AI Model.
Model updates, API guides, benchmarks, and practical insights for building faster with CometAPI.
Guide
How to Use Gemini Omni Fast API
How to Use Gemini Omni Fast API: Master Gemini Omni Fast API for text-to-video, image-to-video, and conversational editing. Try CometAPI. 500+ models.
A
Anna
New
What is Gemini Embedding 2?
Gemini Embedding 2 is Google's first natively multimodal embedding model that maps text, images, audio, video, and PDFs into a single 3,072-dimensional semantic vector space (with configurable output sizes). It introduces Matryoshka Representation Learning to provide nested / truncated embeddings, improved multilingual performance (100+ languages), and optimized controls for task-specific embeddings (e.g., task:search, task:code).
A
Anna
Guide
How to Use Gemini 3.1 pro API
A practical, code-forward guide to Gemini 3.1 Pro โ what it is, how to call it (including via CometAPI), its multimodal and โthinking levelโ controls, function-calling/tool use, vibe-coding tips, and integrations with GitHub Copilot, VS Code, the Gemini CLI, and Google Antigravity. Gemini 3.1 pro is rolling forward the frontier of large multimodal models with a focused developer story: bigger context windows, configurable โthinkingโ modes, improved tool- and function-calling, and explicit support for agentic workflows.
A
Anna
Technology
Gemini API: what file sizes & input methods are supported now?
On January 12, 2026 Google published a developer update to the Gemini API that changes how you get files into the model and how large those files can be. In short: Gemini now fetches files directly from external links and cloud storage (so you don't always have to upload them), and the inline file size limit has been raised substantially. These updates remove friction for real-world apps that already store media or documents in cloud buckets, and make short prototyping and production workflows faster and cheaper.
A
Anna