All integrations
Inference Provider
SIMBA + Cloudflare Workers AI
Run LLM inference at the edge via Cloudflare Workers AI.
Cloudflare Workers AI API docsRoute your agent's LLM calls to Cloudflare Workers AI for low-latency, edge-hosted inference. Strong fit for globally distributed callers.
What agents can do
- Edge LLM inference
- OpenAI-compatible endpoint
- Cost-effective at scale
Common workflows
Global agent footprint
Callers across geos get low-latency inference from the nearest Cloudflare region.
Setup
- 1Create a Cloudflare API token with Workers AI scope.
- 2Add the Cloudflare integration in SIMBA.
- 3Set your agent's LLM provider to Cloudflare Workers AI.
Frequently asked questions
Which models are available?
Llama, Mistral, Qwen, and others. Check Cloudflare's catalog for the current list.
Connect Cloudflare Workers AI in the dashboard
Bring your own credentials. SIMBA stores them server-side and your agents call Cloudflare Workers AI during conversations.