BroadRouter

Cloudflare Workers AI API pricing

Updated

Cloudflare Workers AI lists standard prices for 40 models. The cheapest is Granite 4.0 H Micro at USD 0.017 input and USD 0.112 output per 1M tokens; the dearest is GLM 5.3 at USD 1.40 / USD 4.40. It publishes cached-input prices for 10 of them, and lists no per-model batch, flex or priority prices on the pages we read.

Cloudflare Workers AI hosts models it does not train. By maker: Meta 14, DeepSeek 4, Qwen 4, Z.ai 4, Moonshot AI 3, Google 2, and 7 more. 40 prices, each read from Cloudflare Workers AI's own pricing page, checked 2026-11-14. BroadRouter is BroadNet's own site and does not sell Cloudflare Workers AI's services. Automated re-check 2026-11-16: 40 of 40 prices still matched the provider's page.

Models with a standard price
40
Median input / output
USD 0.2965 / USD 0.7885
Cached-input prices
10 of 40
Cheapest host for
4 of 29 shared models

Which models is Cloudflare Workers AI the cheapest provider for?

Of the 29 models that Cloudflare Workers AI and at least one other provider both price at the standard tier, Cloudflare Workers AI has the lowest price for 4, ranked on a blend of 3 input tokens to 1 output token (1 of them tied with another provider at the same price). It is the dearest for 12. Another 11 models have a standard price from Cloudflare Workers AI only.

Models where Cloudflare Workers AI is the cheapest provider
ModelCloudflare Workers AI input / outputNext cheapestSaving on 3:1 blendProviders
GLM 4.7 FlashUSD 0.06 / USD 0.40Featherless USD 0.0653 / USD 0.403%5
Llama 3.2 1B InstructUSD 0.027 / USD 0.201Featherless USD 0.027 / USD 0.201tie3
Qwen3 30B A3B (fp8)USD 0.051 / USD 0.335GMI Cloud USD 0.08 / USD 0.25under 1%3
Qwen2.5 Coder 32B InstructUSD 0.66 / USD 1Featherless USD 0.68 / USD 1.208%2

The 6 models Cloudflare Workers AI sells that the most other providers also sell, with Cloudflare Workers AI's rank among them on the 3:1 blend.

Cloudflare Workers AI on the most widely hosted models
ModelCloudflare Workers AIRankCheapest
GLM 5.3USD 1.40 / USD 4.406 of 24DeepInfra USD 0.5625 / USD 2.50
OpenAI GPT OSS 120BUSD 0.35 / USD 0.7520 of 21CoreWeave Forge USD 0.03 / USD 0.17
GLM 5.3 FlashUSD 0.15 / USD 0.503 of 20GMI Cloud USD 0.075 / USD 0.25
GLM 5.2USD 1.40 / USD 4.405 of 19DeepInfra USD 0.5625 / USD 1.80
DeepSeek V4.1 Flash 1017USD 0.30 / USD 1.206 of 16DeepInfra USD 0.098 / USD 0.294
DeepSeek V4 Pro 0813USD 1.32 / USD 3.965 of 15Chutes USD 0.85 / USD 2.65

Which model makers does Cloudflare Workers AI sell?

Cloudflare Workers AI prices models from 13 makers. Meta leads with 14 models. Standard prices, USD per 1M input / output tokens.

Cloudflare Workers AI models by maker
MakerModelsCheapest modelMedian input / output
Meta14Llama 3.2 1B Instruct USD 0.027 / USD 0.201USD 0.211 / USD 0.53
DeepSeek4DeepSeek V4.1 Flash 1017 USD 0.30 / USD 1.20USD 0.4685 / USD 2.64
Qwen4Qwen3 30B A3B (fp8) USD 0.051 / USD 0.335USD 0.555 / USD 1
Z.ai4GLM 4.7 Flash USD 0.06 / USD 0.40USD 0.775 / USD 2.45
Moonshot AI3Kimi K2.5 USD 0.60 / USD 3USD 0.95 / USD 4
Google2Gemma 4 26B A4B USD 0.10 / USD 0.30USD 0.2225 / USD 0.428
Mistral AI2Mistral 7B Instruct v0.1 USD 0.11 / USD 0.19USD 0.2305 / USD 0.3725
OpenAI2GPT OSS 20B USD 0.20 / USD 0.30USD 0.275 / USD 0.525
AI Singapore1Gemma SEA-LION v4 27B USD 0.351 / USD 0.555—
Daily1PhoneLLM Mini Alpha 2 USD 0.06 / USD 0.24—
IBM1Granite 4.0 H Micro USD 0.017 / USD 0.112—
NVIDIA1NVIDIA Nemotron 3 Super 120B A12B USD 0.50 / USD 1.50—
Thinking Machines1Inkling 2 Small USD 0.30 / USD 1—

Cloudflare Workers AI price list

USD per 1M tokens: 40 prices for 40 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means Cloudflare Workers AI is cheaper. Of 8 hosted model prices with a maker price to compare, 0 are below the maker's and 1 above.

Cloudflare Workers AI API prices by model
ModelTierInputCachedOutputContextvs makerSource
DeepSeek R1 Distill Qwen 32BstandardUSD 0.497—USD 4.881not stated—source
DeepSeek V4 Flash 0731standardUSD 0.44USD 0.014USD 1.32not stated—source
DeepSeek V4 Pro 0813standardUSD 1.32USD 0.044USD 3.96not statedsamesource
DeepSeek V4.1 Flash 1017standardUSD 0.30USD 0.006USD 1.20not statedsamesource
Gemma 3 12BstandardUSD 0.345—USD 0.556not stated—source
Gemma 4 26B A4BstandardUSD 0.10—USD 0.30not stated—source
Gemma SEA-LION v4 27BstandardUSD 0.351—USD 0.555not stated—source
GLM 4.7 FlashstandardUSD 0.06—USD 0.40not stated—source
GLM 5.2standardUSD 1.40USD 0.26USD 4.40not statedsamesource
GLM 5.3standardUSD 1.40USD 0.26USD 4.40not statedsamesource
GLM 5.3 FlashstandardUSD 0.15USD 0.03USD 0.50not statedsamesource
GPT OSS 20BstandardUSD 0.20—USD 0.30not stated—source
Granite 4.0 H MicrostandardUSD 0.017—USD 0.112not stated—source
Inkling 2 SmallstandardUSD 0.30USD 0.10USD 1not stated—source
Kimi K2.5standardUSD 0.60USD 0.10USD 3not stated—source
Kimi K2.6standardUSD 0.95USD 0.16USD 4not statedsamesource
Kimi K2.7 CodestandardUSD 0.95USD 0.19USD 4not statedsamesource
Llama 2 7B Chat (fp16)standardUSD 0.556—USD 6.667not stated—source
Llama 3 8B InstructstandardUSD 0.282—USD 0.827not stated—source
Llama 3 8B Instruct (AWQ)standardUSD 0.123—USD 0.266not stated—source
Llama 3.1 8B InstructstandardUSD 0.282—USD 0.827not stated—source
Llama 3.1 8B Instruct (AWQ)standardUSD 0.123—USD 0.266not stated—source
Llama 3.1 8B Instruct (fp8-fast)standardUSD 0.045—USD 0.384not stated—source
Llama 3.1 8B Instruct (fp8)standardUSD 0.152—USD 0.287not stated—source
Llama 3.1 Instruct (70B)standardUSD 0.293—USD 2.253not stated—source
Llama 3.2 11B Vision InstructstandardUSD 0.049—USD 0.676not stated—source
Llama 3.2 1B InstructstandardUSD 0.027—USD 0.201not stated—source
Llama 3.2 3B InstructstandardUSD 0.051—USD 0.335not stated—source
Llama 3.3 70BstandardUSD 0.293—USD 2.253not stated—source
Llama 4 Scout 17B 16E InstructstandardUSD 0.27—USD 0.85not stated—source
Llama Guard 3 8BstandardUSD 0.484—USD 0.03not stated—source
Mistral 7B Instruct v0.1standardUSD 0.11—USD 0.19not stated—source
Mistral Small 3.1 24B InstructstandardUSD 0.351—USD 0.555not stated—source
NVIDIA Nemotron 3 Super 120B A12BstandardUSD 0.50—USD 1.50not stated—source
OpenAI GPT OSS 120BstandardUSD 0.35—USD 0.75not stated—source
PhoneLLM Mini Alpha 2standardUSD 0.06—USD 0.24not stated—source
Qwen2.5 Coder 32B InstructstandardUSD 0.66—USD 1not stated—source
Qwen3 30B A3B (fp8)standardUSD 0.051—USD 0.335not stated—source
Qwen3.8 27BstandardUSD 0.45—USD 3.20not stated+1%source
QwQ 32BstandardUSD 0.66—USD 1not stated—source
  • Cached "—" means Cloudflare Workers AI's page shows no cache price for that row; budget cached tokens at the input price.
  • Context "not stated": Cloudflare Workers AI's pricing page does not give context windows.

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What service tiers does Cloudflare Workers AI publish?

Standard prices only: Cloudflare Workers AI publishes no per-model batch, flex, priority or fast price on the pages we read.

Cached input: 10 of 40 standard prices include a cache-read price, a median 18% of the input price. What cached input means.

What we recorded about Cloudflare Workers AI's pricing page: Billed in neurons at $0.011 per 1,000 neurons; the pricing page publishes the equivalent USD per-1M-token price for each LLM, which is used here directly (no conversion needed). Context windows are not stated on the pricing page.

Is Cloudflare Workers AI cheaper than the model makers' own APIs?

Mostly it charges the same as the maker. Of 8 standard prices for models whose maker sells its own API, 0 are below the maker's price, 1 above and 7 the same, on the 3:1 blend. The median difference is zero. The biggest markup is Qwen3.8 27B, 1% above Alibaba Cloud.

BroadNet Inference and Cloudflare Workers AI

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 3 models that Cloudflare Workers AI prices: BroadNet Gemma 4 VL 26B at USD 0.10 / USD 0.22 against Cloudflare Workers AI's USD 0.10 / USD 0.30 (BroadNet is cheaper on the 3:1 blend); Qwen3.8 27B at USD 0.175 / USD 2.17 against Cloudflare Workers AI's USD 0.45 / USD 3.20 (BroadNet is cheaper on the 3:1 blend); GLM 5.3 at USD 0.78 / USD 3.46 against Cloudflare Workers AI's USD 1.40 / USD 4.40 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.

More on Cloudflare Workers AI

Questions

How much does the Cloudflare Workers AI API cost per token?

Cloudflare Workers AI's standard prices run from USD 0.017 input and USD 0.112 output per 1M tokens (Granite 4.0 H Micro) to USD 1.40 / USD 4.40 (GLM 5.3). The median across 40 standard prices is USD 0.2965 input and USD 0.7885 output per 1M, which is USD 0.0000002965 per input token. Input, cached input and output are billed separately.

What is the cheapest model on Cloudflare Workers AI?

Granite 4.0 H Micro, at USD 0.017 input and USD 0.112 output per 1M tokens (USD 0.04075 on a 3:1 input-to-output blend). The cheapest from other makers: Llama 3.2 1B Instruct (Meta) at USD 0.027 / USD 0.201; DeepSeek V4.1 Flash 1017 (DeepSeek) at USD 0.30 / USD 1.20; Qwen3 30B A3B (fp8) (Qwen) at USD 0.051 / USD 0.335.

Is Cloudflare Workers AI cheaper than other providers?

It depends on the model. Of 29 models that other providers also price, Cloudflare Workers AI is the cheapest standard price for 4 (1 of them tied with another provider), for example GLM 4.7 Flash, Llama 3.2 1B Instruct and Qwen3 30B A3B (fp8); another provider is cheaper for 25; and it is the dearest for 12. Its median rank is 4 of a median 6 providers, on a 3:1 input-to-output blend.

Does Cloudflare Workers AI have batch, cached or priority pricing?

Cached input: yes, for 10 of 40 standard prices, at a median 18% of the input price. No batch, flex or priority prices are listed per model on the pages we read.

How much does a chatbot cost per month on Cloudflare Workers AI?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 3.55 on Granite 4.0 H Micro, USD 40.27 on Llama 3.1 8B Instruct (the middle of Cloudflare Workers AI's list) and USD 170.05 on Llama 2 7B Chat (fp16). Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity