Agent infrastructure

Durable multi-step applications on Cloudflare Workers that can wait for events or approvals.

APIs that turn public web pages and entities into structured, verified facts for AI applications.

Search API for AI agents over public web and private information, with a hosted MCP server.

Inference cloud for open-weight and custom models, with 99.99% uptime SLAs and dedicated GPU endpoints.

Secure microVM and gVisor sandboxes for untrusted and agent-generated code, on Northflank Cloud or your own cloud.

Hosted model APIs, GPU cloud and agent sandboxes on one platform, with token-based billing for models.

Search, scrape, crawl and answer API for AI agents that returns clean Markdown, HTML and structured JSON.

Unified OpenAI-compatible API in front of hundreds of LLMs, with routing, fallbacks and cost tracking.

Real-time SERP API for scraping Google results as JSON, with pay-per-successful-search pricing.

Web access API for AI agents with real-time search, extraction, crawling and research endpoints.

Cloud platform for running, fine-tuning and serving open-source AI models behind an OpenAI-compatible API.

Hybrid retrieval engine built on object storage, with semantic, keyword, dense, sparse and multi-vector search.

Serverless vector database with dense, sparse and hybrid indexes for semantic and keyword search.

Platform for deploying apps and AI agents, with an AI Gateway, sandboxes and fluid compute.

Web data infrastructure for agents: Fetch, Extract, Crawl, Batch and Browser Sessions over API, CLI, MCP or SDK.

Web scraping API with automatic ban handling, browser rendering, sessions and extraction, plus a Python client.

Full Linux VMs for long-running agent tasks, with millisecond startup, live cloning and pause and resume.

Access to hundreds of open models from partner inference providers through one Hugging Face token and SDK.

GPU cloud for AI training and inference, with on-demand instances, 1-Click Clusters and private clusters.

One API for open and commercial LLM and multimodal models, with pay-as-you-go pricing and fast inference.

Desktop app for running open LLMs locally, with a built-in agent called Bionic.

Cloud browsers for AI agents with managed authentication, natural-language tasks and stealth browsing.

Build, test and deploy voice, chat and email AI agents for websites, apps and call centers, in 90+ languages.

Platform for creating and managing VM-based remote runtimes for AI agents, with snapshots, SSH and a Python SDK.