Cloudflare Workers AI API pricing
23 models · USD per 1M tokens · verified 2026-10-23
Cloudflare Workers AI serves 23 of the models we track, 23 of them open-weights. The cheapest is Llama 3.2 1B Instruct at $0.027 input and $0.201 output per million tokens. For 8 of these models, Cloudflare Workers AI is the cheapest tracked host.
// models on Cloudflare Workers AI
| model | lab | in $/1M | out $/1M | ctx | vs best price |
|---|---|---|---|---|---|
| Llama 3.2 1B Instruct BEST | Meta | $0.027 | $0.201 | 60K | best |
| Qwen3 30B A3b fp8 BEST | Alibaba (Qwen) | $0.0509 | $0.335 | 32.8K | best |
| Llama 3.2 3B Instruct BEST | Meta | $0.0509 | $0.335 | 80K | best |
| Gemma 4 26B A4B IT | $0.10 | $0.30 | 262.1K | +9.1% | |
| Llama-3.1-8B-Instruct | Meta | $0.152 | $0.287 | 16.4K | +575.3% |
| Llama 3.2 11B Vision Instruct BEST | Meta | $0.0485 | $0.676 | 128K | best |
| GPT OSS 20B | OpenAI | $0.20 | $0.30 | 131.1K | +291.3% |
| GLM-5.3-FlashX BEST | Z.AI (Zhipu) | $0.15 | $0.50 | 1M | −59.7% |
| Llama Guard 3 8B BEST | Meta | $0.484 | $0.03 | 131.1K | best |
| Mistral Small 3.1 24B | Mistral | $0.351 | $0.555 | 128K | +168% |
| Llama 4 Scout 17B | Meta | $0.27 | $0.85 | 327.7K | +176.7% |
| GPT OSS 120B | OpenAI | $0.35 | $0.75 | 131.1K | +540.1% |
| DeepSeek V4 Flash 0731 | DeepSeek | $0.44 | $1.32 | 1.05M | +633.3% |
| Qwen2.5 Coder 32B Instruct BEST | Alibaba (Qwen) | $0.66 | $1.00 | 32.8K | best |
| Qwq 32B BEST | Alibaba (Qwen) | $0.66 | $1.00 | 24K | best |
| Llama 3.3 70B Turbo | Meta | $0.293 | $2.253 | 131.1K | +405.2% |
| Qwen3.8 27B | Alibaba (Qwen) | $0.45 | $3.20 | 262.1K | +46.8% |
| DeepSeek R1 (Turbo) | DeepSeek | $0.497 | $4.881 | 64K | +38.5% |
| Kimi K2.6 | Moonshot AI | $0.95 | $4.00 | 262.1K | best |
| Kimi K2.7 Code HighSpeed | Moonshot AI | $0.95 | $4.00 | 262.1K | −50% |
| DeepSeek V4 Pro (0813) | DeepSeek | $1.32 | $3.96 | 1.05M | +100% |
| GLM-5.2 | Z.AI (Zhipu) | $1.40 | $4.40 | 1M | best |
| GLM-5.3 | Z.AI (Zhipu) | $1.40 | $4.40 | 1M | best |
// how to read this page
Prices are Cloudflare Workers AI's base-tier list prices per million tokens. "vs best price" compares Cloudflare Workers AI's blended price (3 × input + output) / 4 with the lowest price we track for the same model, whether it comes from the lab's own API or another host. Open each model for its full price history and every host that serves it.