LLM Reference
Cloudflare Workers AI

Cloudflare Workers AI

Cloudflare

Hyperscaler

Platform

Cloudflare Workers AI is a serverless platform that enables developers to run machine learning models on a global network powered by GPUs. The platform supports a wide range of AI tasks, including text generation, image classification, automatic speech recognition, and real-time language translation. It offers a comprehensive library of curated open-source models, allowing developers to easily deploy AI applications without the need for complex infrastructure management. Key features include low-latency edge computing, enhanced security for AI models, and scalability to meet varying demands. The platform integrates seamlessly with popular AI models and tools, including those from Hugging Face, facilitating one-click deployment of applications. Advanced capabilities such as streaming responses for large language models, increased context lengths for improved interaction, and fine-tuning options for model customization are also available. Additionally, the AI Gateway enhances application performance through monitoring, caching, and cost management features, enabling developers to optimize their AI solutions effectively. This comprehensive suite of tools and features empowers developers to build and deploy innovative AI applications rapidly and cost-effectively across various sectors.

About Cloudflare

Cloudflare does not have a dedicated AI platform as its primary focus. Instead, Cloudflare is a leading connectivity cloud company that provides a comprehensive suite of cloud-native products and developer tools to enhance web performance, security, and reliability. Their services include content delivery network (CDN), DDoS mitigation, DNS services, and zero trust security solutions. While Cloudflare doesn't offer a standalone AI platform, they do incorporate AI and machine learning technologies into various aspects of their services to improve performance and security. For example, they use AI to enhance their threat detection capabilities, optimize content delivery, and provide more intelligent routing decisions across their global network. Cloudflare's main focus is on providing a unified platform that helps organizations make their employees, applications, and networks faster and more secure while reducing complexity and cost. Their services are trusted by millions of organizations worldwide, from large enterprises to small businesses and non-profits.

Available Models(20)

ModelInput (per 1M)Output (per 1M)Type
Hermes 2 Pro Mistral 7B
Serverless
Llama 3 8B Instruct
Serverless
Llama 2 13B Chat
Serverless
Llama 2 7B Chat
Serverless
Mistral 7B v0.1
Serverless
DeepSeek Coder 6.7B
Serverless
DeepSeek Math 7B
Serverless
Falcon 7B
Serverless
Gemma 2B Instruct
Serverless
Gemma 7B Instruct
Serverless
Llama Guard 7B
Serverless
OpenChat 3.5 (0106)
Serverless
Phi-2
Serverless
OpenHermes 2.5 Mistral 7B
Serverless
Qwen1.5-0.5B
Serverless
Qwen1.5-1.8B
Serverless
Qwen1.5-7B
Serverless
Qwen1.5-14B
Serverless
Starling LM 7B Beta
Serverless
SQLCoder 7B 2
Serverless

Company Info

Founded2009
San Francisco, California, United States