Cloudflare models
Edge compute and storage products with usage-based add-ons.
Llama 3.3 70B (Workers AI)
$0.293 / $2.253 per 1M tokens
Llama 4 Scout (Workers AI)
$0.27 / $0.85 per 1M tokens
gpt-oss-120b (Workers AI)
$0.35 / $0.75 per 1M tokens
Gemma 4 26B (Workers AI)
$0.1 / $0.3 per 1M tokens
Llama 3.1 8B Instruct FP8 Fast (Workers AI)
$0.045 / $0.384 per 1M tokens
GPT OSS 20B (Workers AI)
$0.2 / $0.3 per 1M tokens
Cloudflare
Edge compute and storage products with usage-based add-ons.
There are 6 published models here. On a 70/30 mix, combined list rates run from $0.1467 to $0.881 per 1 million tokens, with a median of $0.337. The largest listed context window in this group is 131,000 tokens. The most recent price check in this group is 2026-08-14.
Official Cloudflare pricing page
Cloudflare list rates
USD per million tokens. The 70/30 mix is a planning default — change it on the model page if your traffic is output-heavy.
| Model | Input / 1M | Output / 1M | Mixed 70/30 | Context | Verified |
|---|---|---|---|---|---|
| Llama 3.1 8B Instruct FP8 Fast (Workers AI) | $0.045 | $0.384 | $0.1467 | 128,000 | |
| Gemma 4 26B (Workers AI) | $0.1 | $0.3 | $0.16 | 128,000 | |
| GPT OSS 20B (Workers AI) | $0.2 | $0.3 | $0.23 | 128,000 | |
| Llama 4 Scout (Workers AI) | $0.27 | $0.85 | $0.444 | 131,000 | |
| gpt-oss-120b (Workers AI) | $0.35 | $0.75 | $0.47 | 128,000 | |
| Llama 3.3 70B (Workers AI) | $0.293 | $2.253 | $0.881 | 128,000 |
Questions about Cloudflare rates
Do these Cloudflare figures include discounts and tax?
No. They are public list rates. Commits, credits, regions, tax, and commercial discounts are not in the number — check the source linked on each model.
When is the more expensive Cloudflare tier worth the extra?
Llama 3.3 70B (Workers AI) sits near $0.881 per 1M tokens on a 70/30 mix, versus $0.1467 on Llama 3.1 8B Instruct FP8 Fast (Workers AI). Use the high tier when retries or long reasoning actually fail on the cheap one.