All tasks / Tools
Cloudflare Workers AI
Serverless inference on Cloudflare's network for open-weight LLMs and other models, called from Workers or a REST API.
- Cloudflare
- Cloud
- Free tier · paid plans
Where it ranks
- AChat & assistantsRuntimes & gateways · Cloud · via GLM-5.3
- CCodingRuntimes & gateways · Cloud · via GLM-5.3
Tools without a benchmark of their own inherit the tier of the best model they offer.
Facts
- Vendor
- Cloudflare
- Approach
- Runtimes & gateways
- Where it runs
- Cloud only: needs the vendor’s service
- Interface
- API
- Skill level
- Advanced: command line, node graphs or self-hosting
- Price
- Free tier · paid plans
- Pricing notes
- 10,000 Neurons/day free; beyond that $0.011 per 1,000 Neurons on the Workers Paid plan (plan fee not on this page).
- Source code
- Closed source
- Last verified
- 19 Oct 2026
Price from developers.cloudflare.com, 19 Oct 2026.
Models it gives you
- AGLM-5.3Z.ai · open weights
- AGLM-5.3-FlashZ.ai · open weights
- ADeepSeek-V4-Pro-0813DeepSeek · open weights
- AGemma 4 (31B)Google DeepMind · open weights
- AQwen3.8-27BAlibaba (Qwen) · open weights
- Bgpt-oss-120bOpenAI · open weights
- Cgpt-oss-20bOpenAI · open weights