kitio.aiAdded Oct 28, 2026
Cloudflare Workers AI
Freemium · $5/moServerless inference for open models on Cloudflare's global network
What is Cloudflare Workers AI?
Cloudflare Workers AI runs open-source models for text, images, speech and embeddings on GPUs across Cloudflare's network. Developers call it from Workers code or a REST API, which keeps inference close to users with no servers to manage.
It pairs with Vectorize for vector search, AI Gateway for caching and analytics, and the Agents SDK for stateful agents. The Replicate catalog, which Cloudflare acquired, is being folded into the platform.
A daily free allowance covers light use, and usage beyond it is billed in neurons on the Workers Paid plan. LoRA adapters can be loaded for some models.
Features
- Global GPU inference
- Text, image and speech models
- Vectorize integration
- AI Gateway
- LoRA support
Tags
Releases
+ Submit new release- Listed
Cloudflare Workers AI was added to the directory.
Organization
Cloudflare
🇺🇸 United States
Listed by kitio.ai · unverified owner
Pricing
- Pricing model
- Freemium
- Paid options from
- $5/mo
- Billing frequency
- Monthly
Cloudflare Workers AI plans
Workers Free
Free
- 10,000 Neurons per day
- Fails with error past daily limit
Workers Paid
$5/mo
- 10,000 free Neurons per day
- Then $0.011 per 1,000 Neurons
Prices in USD, checked Oct 28, 2026. Plans change often, so confirm on the Cloudflare Workers AI site.Official pricing
Sponsored
Your AI tool here
A Featured launch puts your tool in this spot and on the home page for a week.
Top Cloudflare Workers AI alternatives
View allModels & APIs
On-demand GPU pods and serverless endpoints for AI workloads
Models & APIs
Serverless cloud for running Python and GPU workloads on demand
Models & APIs
Production inference and fine-tuning for open models on Nebius cloud
Compare Cloudflare Workers AI
If you liked Cloudflare Workers AI
Fast inference for large open models on SambaNova's RDU chips
FreemiumModels & APIsMade in United StatesInference cloud for open models like DeepSeek, Qwen and GLM
FreemiumModels & APIsMade in ChinaServerless vector database with per-request pricing and a free tier
FreemiumModels & APIsMade in United StatesSmall task-specific open models for search, extraction and classification
PaidModels & APIs
Pros and cons
Pros
- No servers to manage
- Daily free allowance
- Fits the Cloudflare developer stack
Cons
- Smaller models than big labs offer
- Neuron pricing is unusual
- Best inside Cloudflare Workers
Prompts & results
No prompts yet. Add your own prompt and output to help others use this tool.
Share a prompt
Reviews
Q&A
What is Cloudflare Workers AI?
Cloudflare Workers AI runs open-source models for text, images, speech and embeddings on GPUs across Cloudflare's network. Developers call it from Workers code or a REST API, which keeps inference close to users with no servers to manage.
How much does Cloudflare Workers AI cost?
Cloudflare Workers AI is freemium, with paid plans from $5/mo.
Is there a free version of Cloudflare Workers AI?
Yes. Cloudflare Workers AI has a free plan, and paid plans add more usage and features.
What are the main features of Cloudflare Workers AI?
Global GPU inference, Text, image and speech models, Vectorize integration, AI Gateway, LoRA support.
Who makes Cloudflare Workers AI?
Cloudflare Workers AI is made by Cloudflare.
What are the best alternatives to Cloudflare Workers AI?
Popular alternatives include Featherless, RunPod, Modal.