Workers AI
Model inference inside Cloudflare Workers.
Key features
- Run machine learning models on serverless GPUs
- Call models from Workers, Pages, or the API
- Use 50+ open-source models from the catalog
- Classify images, generate text, and detect objects
- Fine-tune models with LoRA adapters
- Category
- LLM APIs
- Who it's for
- Developers who run AI models from their own code on Cloudflare.
- Tags
- cloudflareinferencellm-apiopen-modelsgpufine-tuningserverlessimage-video
- Website
- developers.cloudflare.com
- Listed
- 2026-09-15
Sourced notes
Frequently asked questions
Is Workers AI free?
Workers AI has a free plan, with paid tiers for more usage or features.
How much does Workers AI cost?
Paid plans from $0.011 / 1,000 Neurons, according to its pricing page.
What is Workers AI used for?
Model inference inside Cloudflare Workers. Typical uses: run machine learning models on serverless GPUs; call models from Workers, Pages, or the API; use 50+ open-source models from the catalog.
What are the best Workers AI alternatives?
Alternatives in the same category include Cerebras, Together AI, DeepInfra, fal, Fireworks AI.
Related in LLM APIs
See all →- Cerebras Wafer-scale inference for open models.
- DeepInfra Hosted inference API for open models.
- Fireworks AI Inference platform for open models.
- Groq Inference API known for low-latency open models.
- Hugging Face Model hub, datasets, and hosted inference.
- NVIDIA NIM NVIDIA's catalog of inference microservices and trial APIs.
