Cloudflare
US · serverless
Workers AI runs inference at the edge, billed in neurons rather than tokens.
- Category
- serverless
- Free tier
- Yes
- OpenAI API
- Compatible
- Adds on top
- None - billed in neurons
Margin over the underlying model price
What Cloudflare charges
Live prices for widely-hosted open-weight models, sampled from the shared catalogue. Compare the same row against other hosts on each model page.
| Model | Input / 1M | Output / 1M | Context | Throughput |
|---|---|---|---|---|
| GLM 5.3 Flash | $0.150 | $0.500 | 1.3M | - |
| DeepSeek V4 Flash 0731 | $0.440 | $1.32 | 1.3M | - |
| Qwen3.8 27B | $0.450 | $3.20 | 262K | - |
| DeepSeek V4 Pro 0813 | $1.32 | $3.96 | 1.0M | - |
| GLM 5.3 | $1.40 | $4.40 | 1.3M | - |
Cloudflare alternatives
Other services in the same category. These are genuine substitutes - services in a different category solve a different problem.
Frequently asked
Is Cloudflare OpenAI-compatible?
Yes. Cloudflare accepts the OpenAI chat-completions request shape, so most SDKs work by changing the base URL and API key.
Does Cloudflare have a free tier?
Yes - Cloudflare offers free usage, though limits and eligible models change frequently. Check the pricing page before relying on it.
How does Cloudflare charge?
Neurons, with a free daily allocation Margin over the underlying model price: none - billed in neurons.