Cloudflare
Cloudflare runs a global network for websites and applications. Workers AI sells open models per token on its GPUs, billed in neurons, with no region to choose.
- Website: https://www.cloudflare.com
- Headquarters: San Francisco, United States
- Kind: Edge network, Per-token API
Cloudflare sells 16 of the compared models per token and prices 0 kinds of GPU for hosting your own.
Models sold per token
| Model | Input, per 1M tokens | Output, per 1M tokens |
|---|---|---|
| DeepSeek V4 Flash 0731 | $0.44 | $1.32 |
| DeepSeek V4 Pro 0813 | $1.32 | $3.96 |
| Gemma 4 26B A4B | $0.10 | $0.30 |
| GLM 5.2 | $1.40 | $4.40 |
| GLM 5.3 | $1.40 | $4.40 |
| GLM 5.3 Flash | $0.15 | $0.50 |
| Kimi K2.5 | $0.60 | $3.00 |
| Kimi K2.6 | $0.95 | $4.00 |
| Kimi K2.7 Code | $0.95 | $4.00 |
| Llama 3.1 70B | $0.293 | $2.25 |
| Llama 3.1 8B | $0.045 | $0.266 |
| Llama 3.3 70B | $0.293 | $2.25 |
| Llama 4 Scout 17B | $0.27 | $0.85 |
| OpenAI gpt-oss 120B | $0.35 | $0.75 |
| OpenAI gpt-oss 20B | $0.20 | $0.30 |
| Qwen3.8 27B | $0.45 | $3.20 |
Where it runs
One global price; Cloudflare chooses where a request is processed.
No place stated for 16 models: one global price, and Cloudflare does not say where a request is processed.
Where the prices come from
- Per-token prices: developers.cloudflare.com/workers-ai/platform/pricing/index.md
Sources
List prices collected 4 November 2026, refreshed every three hours. No negotiated rates or taxes.