Cloudflare Workers AI
Run AI models at the edge on Cloudflare's global network with serverless inference and low latency.
Cloudflare Workers AI
Run AI models at the edge on Cloudflare's global network with serverless inference and low latency.
Authentication
API KeyAdd your Cloudflare Workers AI API key from Organization → Integrations → AI Vendors. Keys are encrypted at rest and scoped to your organization.
Available Models
8 enabled models across 1 category.
Text8
@cf/google/gemma-4-26b-a4b-itchatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
@cf/zai-org/glm-4.7-flashchatModel, languageModel, completionModel
functionCalling, reasoning
@cf/openai/gpt-oss-120bchatModel, languageModel, completionModel
functionCalling, reasoning
@cf/openai/gpt-oss-20bchatModel, languageModel, completionModel
functionCalling, reasoning
@cf/moonshotai/kimi-k2.5chatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
@cf/moonshotai/kimi-k2.6chatModel, languageModel, completionModel
functionCalling, reasoning, imageInput, vision
@cf/meta/llama-4-scout-17b-16e-instructchatModel, languageModel, completionModel
functionCalling, imageInput, vision
@cf/nvidia/nemotron-3-120b-a12bchatModel, languageModel, completionModel
functionCalling, reasoning