{"rid":"inference/cloudflare-workers-ai","card":{"rid":"inference/cloudflare-workers-ai","eid":"cloudflare","topic":"inference","slug":"cloudflare-workers-ai","provider":"Cloudflare Workers AI","url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","domain":"cloudflare.com","category":"inference endpoint, platform allocation","tier":null,"verdict":"qualifies-with-caveat","vorder":1,"grp":"usable","confidence":"documented","binding":"request-rate","identity_kind":"email","identity_basis":"stated","needs_card":0,"needs_phone":0,"needs_id":0,"needs_institution":0,"country":null,"crypto":null,"interfaces":"rest","egress_metered":0,"per_object_bytes":null,"retention_days":null,"verified_at":"2026-10-22T04:31:58.000Z","verified_basis":"live","checked_on":"2026-10-23","stale_on":"2026-11-22","n_evidence":3,"usd_month":null,"usd_per_tb_month":null,"summary":"10,000 Neurons per day at no charge on both the Free and the Paid Workers plan. The page states the daily figure; the monthly figure of 300,000 and the token...","duplicate_of":null,"n_unknown":1},"record":{"topic":"inference","per_object_cap":{"stated":"not applicable: an inference endpoint stores nothing for the caller"},"retention":{"stated":"not applicable"},"egress":{"terms":"the response is the payload; no separate egress term is published","metered":false},"interface":["rest"],"tooling":"any OpenAI-compatible client; curl against POST {base}/chat/completions","chaining":"pairs with a Cloudflare Worker already deployed; the 300,000-neuron monthly allowance is the scarce link, and it covers 42 per cent of the target workload","limits":[{"kind":"request-rate","value":"10,000 Neurons per day, reset at 00:00 UTC; further operations fail with an error past it","source":"https://developers.cloudflare.com/workers-ai/platform/pricing/, read 2026-10-22"},{"kind":"request-rate","value":"300 requests a minute for text generation on the documented tier, unless the model requires the Workers Paid plan; the 3,000-a-minute figure on the same page belongs to image classification, object detection and text embeddings","source":"https://developers.cloudflare.com/workers-ai/platform/limits/, read 2026-10-22"},{"kind":"request-rate","value":"20 requests a minute per account per model on standard billing for the eight paid-only models, 50 requests a minute with prepaid AI Gateway credits","source":"https://developers.cloudflare.com/workers-ai/platform/limits/, read 2026-10-22"}],"slug":"cloudflare-workers-ai","provider":"Cloudflare Workers AI","url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","category":"inference endpoint, platform allocation","free_tier":{"stated":"10,000 Neurons per day at no charge on both the Free and the Paid Workers plan. The page states the daily figure; the monthly figure of 300,000 and the token equivalents below are derived arithmetic on it, not vendor statements","unit":"tokens","metered_on":"request-count","source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","read_on":"2026-10-22","notes":"billing is in Neurons. The page prints a per-token price beside each model as an equivalent, so a single USD per million tokens figure for Workers AI does not exist. The free-plan input rate runs from 1,542 to 60,000 neurons per million tokens across 31 models, a factor of 38.9, so the token count behind one allowance is model-dependent: 194.6 million a month at the cheapest and 5.0 million at the dearest Derived figures and their bases: 300,000 = 10,000 x 30 days; 122.1 million input tokens = 300,000 / 2,457 x 1,000,000; 4.07 million a day = that divided by 30"},"endpoint":"https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/","identity_cost":{"kind":"email","detail":"a Cloudflare account; the Workers Free plan is enough for the daily allocation","country":null},"reliability_note":"eight named models require a paid billing method and fail on a Free plan","confidence":"documented","confidence_note":"the allocation, the reset and the paid-only model list are quoted from the vendor pages read today. No call was made, because that needs an account.","evidence":[{"url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","date":"2026-10-22","proved":"10,000 Neurons per day free, USD 0.011 per 1,000 Neurons above it on Workers Paid, all limits reset daily at 00:00 UTC, and eight named models require a paid billing method including @cf/moonshotai/kimi-k2.6 and @cf/zai-org/glm-5.3-flash"},{"url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","date":"2026-10-22","proved":"per-model neuron rates over 39 text-generation models, of which 31 are reachable on the free plan; input runs from 1,542 neurons per million tokens on @cf/ibm-granite/granite-4.0-h-micro to 60,000 on @cf/qwen/qwq-32b, and the eight paid-only ids run to 127,273 on @cf/zai-org/glm-5.3"},{"url":"https://developers.cloudflare.com/workers-ai/platform/limits/","date":"2026-10-22","proved":"Text Generation is 300 requests per minute, 'unless the model requires the Workers Paid plan'; Image Classification, Object Detection and Text Embeddings are 3000; Summarization 1500; Text Classification 2000; and the eight paid models are 20 requests per minute on standard billing or 50 with prepaid AI Gateway credits"}],"verdict":"qualifies-with-caveat","verified_at":"2026-10-22T04:31:58.000Z","notes":"300,000 Neurons a month, not 375 million: 10,000 a day times 30. At 2,457 neurons per million input tokens that is 122.1 million input tokens a month and 4.07 million a day. The client's target of 15 million input and 37.5 million output tokens a month on llama-3.2-1b-instruct needs 15 x 2,457 + 37.5 x 18,252 = 721,305 neurons, which is 2.4 times the whole free allowance; the output half alone is 2.3 times it. The allocation is real, it is model-dependent, and it cannot carry the target workload, which is why the row is a fallback. Every figure beyond the page's own 10,000 a day is arithmetic on it and is labelled as such in free_tier.stated.","binding":"request-rate"},"claims":[{"path":"$.free_tier.stated","kind":"free-quota","num":null,"unit":null,"per":null,"currency":null,"usd":null,"fx_date":null,"parse":"unparsed"},{"path":"$.limits[0].value","kind":"limit:request-rate","num":null,"unit":null,"per":null,"currency":null,"usd":null,"fx_date":null,"parse":"unparsed"},{"path":"$.limits[1].value","kind":"limit:request-rate","num":300,"unit":"requests","per":"minute","currency":null,"usd":null,"fx_date":null,"parse":"ok"},{"path":"$.limits[2].value","kind":"limit:request-rate","num":20,"unit":"requests","per":"minute","currency":null,"usd":null,"fx_date":null,"parse":"ok"}],"unknown":[["$.retention.stated","not-applicable"]],"history":[{"hid":"history/2026-10-22T044100Z/cloudflare-neuron-month-overstated-1250x.md","when":"2026-10-22T04:41:00Z","status":"corrected","title":"Cloudflare's free allowance was overstated 1,250 times, and the conclusion built on it was void"}],"drift":[]}