• Home
    • Browser Agent
    • Controllable Layer Decomposition
    • Multimodal RAG
    • Cross-Modal Image–Text Retrieval
  • Tech Blog
  • About
Sign in Create account
Workspace

Workspace

Sign in required

Sign in to access your workspace.

Sign in
Overview
API Keys Billing

Models

Overview
Overview API Documentation
Overview API Documentation
Overview API Documentation

Build with intelligence. Work with confidence.

Welcome back. Let’s get started.
Last sign-in: QID:

API keys

View all »

API keys are used for authentication and billing.

Create API key
KEY Created Note Actions
Loading…
Loading…

Billing

Current balance

¥ 0.00

New accounts receive a complimentary ¥50 trial credit.

Add funds
Browser Agent
Browser Agent

Browser Agent

VisFlow learns from your demonstrations and observes, decides, and acts like a person. It can handle both enterprise workflows without APIs and repetitive long-tail consumer tasks.

Overview
Controllable Layer Decomposition
Controllable Layer Decomposition

Controllable Layer Decomposition

Reveal-Layer replaces full-image blind decomposition with controllable, on-demand extraction. Specify a target boundary using bounding-box coordinates or direct selection to isolate an object as an independent RGBA layer, giving users and developers precise, Photoshop-grade layer control.

Overview API Documentation
Multimodal RAG
Multimodal RAG

Multimodal RAG

RzenEmbed is a multimodal embedding model for enterprise document intelligence. It creates unified, high-quality semantic vectors for text, images, video, and mixed-modality documents, supporting cross-modal retrieval, multimodal RAG, and complex document understanding.

Overview API Documentation
Cross-Modal Image–Text Retrieval
Cross-Modal Image–Text Retrieval

Cross-Modal Image–Text Retrieval

FG-CLIP 2 supports long-text, short-text, and fine-grained image–text retrieval in English and Chinese. It provides efficient embedding APIs for text-to-image, image-to-text, text-to-text, and image-to-image retrieval, moving beyond keyword matching for search, recommendations, document intelligence, and semantic video monitoring. Its fine-grained understanding improves long-text retrieval and attribute-level reranking.

Overview API Documentation
360 AI Research 360 AI Research

Making AI simpler and intelligence accessible.

360 AI Research advances frontier AI research and real-world innovation.

Subscribe for research updates RSS Blog Feed

Contact

  • 010-52448983

    Monday–Friday, 09:30–18:30 (China Standard Time)

  • No. 6 Jiuxianqiao Road, Chaoyang District, Beijing

    Electronics City · International Electronics Headquarters

  • 360ai@360.cn

Open-source models

  • Github
  • Hugging Face

Terms & Policies

  • Terms of Use
  • Privacy Policy

Copyright©2026 360.CN All Rights Reserved 360 Internet Security Center

Beijing Public Security Filing No. 11000002002063 Beijing ICP License 080047 · Filing 08010314-6

Full API key

The full key is shown temporarily. Do not share it.