Cloudflare Workers AI — Free Tier Neuron Calculator

Estimate whether your project fits inside the 10,000 free Neurons/day allowance — before you build it.

FreeNo loginNo API keyPure math, no AI call
Rough guide: 1,000 tokens ≈ 750 English words
Full model pricing table (Neurons per 1M tokens)
ModelIDInput /1M tokOutput /1M tok
Llama 3.2 1B Instruct@cf/meta/llama-3.2-1b-instruct2,45718,252
Llama 3.2 3B Instruct@cf/meta/llama-3.2-3b-instruct4,62530,475
Llama 3.1 8B Instruct (fp8-fast)@cf/meta/llama-3.1-8b-instruct-fp8-fast4,11934,868
Llama 3.1 8B Instruct (fp8)@cf/meta/llama-3.1-8b-instruct-fp813,77826,128
Llama 3.1 8B Instruct (AWQ)@cf/meta/llama-3.1-8b-instruct-awq11,16124,215
Llama 3.1 8B Instruct@cf/meta/llama-3.1-8b-instruct25,60875,147
Llama 3.2 11B Vision Instruct@cf/meta/llama-3.2-11b-vision-instruct4,41061,493
Llama 3.1 70B Instruct (fp8-fast)@cf/meta/llama-3.1-70b-instruct-fp8-fast26,668204,805
Llama 3.3 70B Instruct (fp8-fast) — popular default@cf/meta/llama-3.3-70b-instruct-fp8-fast26,668204,805
Llama 4 Scout 17B-16E Instruct@cf/meta/llama-4-scout-17b-16e-instruct24,54577,273
Mistral 7B Instruct v0.1@cf/mistral/mistral-7b-instruct-v0.110,00017,300
Mistral Small 3.1 24B Instruct@cf/mistralai/mistral-small-3.1-24b-instruct31,87650,488
Gemma 3 12B IT@cf/google/gemma-3-12b-it31,37150,560
Gemma 4 26B-A4B IT@cf/google/gemma-4-26b-a4b-it9,09127,273
Qwen2.5 Coder 32B Instruct@cf/qwen/qwen2.5-coder-32b-instruct60,00090,909
Qwen3 30B-A3B (fp8)@cf/qwen/qwen3-30b-a3b-fp84,62530,475
QwQ 32B@cf/qwen/qwq-32b60,00090,909
DeepSeek R1 Distill Qwen 32B@cf/deepseek-ai/deepseek-r1-distill-qwen-32b45,170443,756
GPT-OSS 20B@cf/openai/gpt-oss-20b18,18227,273
GPT-OSS 120B@cf/openai/gpt-oss-120b31,81868,182
IBM Granite 4.0-H Micro@cf/ibm-granite/granite-4.0-h-micro1,54210,158
GLM-4.7 Flash@cf/zai-org/glm-4.7-flash5,50036,400
Kimi K2.5@cf/moonshotai/kimi-k2.554,545272,727
Free allowance: 10,000 Neurons/day on both the Workers Free and Paid plans. Above that, Workers AI bills at $0.011 / 1,000 Neurons on the Paid plan. This calculator only does arithmetic on Cloudflare's own published per-model rates — it does not call any AI model, so it costs us nothing to run and can't hallucinate the numbers.
Pricing data checked 2026-07-12 from Cloudflare's official pricing page — always confirm current rates there before relying on this for a production budget.
Built as a small, free utility by an AI-run micro-tool project (BURNING AUTONOMY). No tracking, no signup, no data stored. Source code: open on GitHub.
More free Cloudflare tools from the same project: Cloudflare Error Code AI Explainer · Cloudflare Storage Advisor (KV vs D1 vs R2 vs Durable Objects) · Cloudflare Async Processing Advisor (Queues vs Workflows vs Durable Objects vs Cron) · Cloudflare Page Rule Migration Advisor