Cloudflare Workers AI
Explore Cloudflare Workers AI models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Cloudflare Workers AIcloudflare-workers-ai
No provider claim
| Provider | Cloudflare Workers AI |
|---|---|
| Provider website | https://www.cloudflare.com/developer-platform/products/workers-ai/ |
| Models | 24 public models |
| Prepaid routes | 24 |
| BYOK routes | 0 |
| Zero data retention | not claimed |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | No provider-ZDR claim is tracked here. Cloudflare's Workers AI documentation is linked for model and data-handling review. Policy source |
Measured performance
30 samplesContinuously sampled across Cloudflare Workers AI's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1481 ms |
|---|---|
| Effective throughput | 22 tok/s n=3 |
| Uptime | 100.00% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| meta-llama/llama-3.1-8b-instruct-fp8 | 765 ms | 765 ms | — | 100.00% | — | 1 |
| meta-llama/llama-3.2-1b-instruct | 1072 ms | 1072 ms | — | 100.00% | — | 3 |
| meta-llama/llama-4-scout-17b-16e-instruct | 1152 ms | 1152 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 1223 ms | 1222 ms | 42 tok/s n=1 | 100.00% | — | 2 |
| qwen/qwq-32b | 1294 ms | 1294 ms | — | 100.00% | — | 1 |
| aisingapore/gemma-sea-lion-v4-27b-it | 1300 ms | 1300 ms | — | 100.00% | — | 4 |
| qwen/qwen2.5-coder-32b-instruct | 1481 ms | 1481 ms | — | 100.00% | — | 2 |
| mistralai/mistral-small-3.1-24b-instruct | 1499 ms | 1499 ms | — | 100.00% | — | 2 |
| meta-llama/llama-3.2-3b-instruct | 2232 ms | 2231 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-r1-distill-qwen-32b | 2388 ms | 2388 ms | — | 100.00% | — | 1 |
| google/gemma-4-26b-a4b-it | 2532 ms | 2531 ms | — | 100.00% | 1 probe_config_error |
2 |
| ibm-granite/granite-4.0-h-micro | 2550 ms | 2550 ms | — | 100.00% | — | 3 |
| openai/gpt-oss-20b | 2710 ms | 2710 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k3 | 2752 ms | 2752 ms | 22 tok/s n=2 | 100.00% | — | 1 |
| qwen/qwen3-30b-a3b-fp8 | 3553 ms | 3552 ms | — | 100.00% | — | 2 |
Cloudflare Workers AI performance history · Full provider & model leaderboard.
Models served by Cloudflare Workers AI.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
aisingapore/gemma-sea-lion-v4-27b-it@cf/aisingapore/gemma-sea-lion-v4-27b-it |
— | 128,000 | 1 | $0.370305/1M | $0.585525/1M | prepaid |
deepseek/deepseek-r1-distill-qwen-32b@cf/deepseek-ai/deepseek-r1-distill-qwen-32b |
— | 80,000 | 1 | $0.524335/1M | $5.149455/1M | prepaid |
deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,048,576 | 1 | $0.4642/1M | $1.3926/1M | prepaid |
google/gemma-4-26b-a4b-itGoogle: Gemma 4 26B A4B |
IQ 96#89 | 262,144 | 1 | $0.1055/1M | $0.3165/1M | prepaid |
ibm-granite/granite-4.0-h-micro@cf/ibm-granite/granite-4.0-h-micro |
— | 131,000 | 1 | $0.017935/1M | $0.11816/1M | prepaid |
meta-llama/llama-3.1-8b-instruct-fp8@cf/meta/llama-3.1-8b-instruct-fp8 |
— | 32,000 | 1 | $0.16036/1M | $0.302785/1M | prepaid |
meta-llama/llama-3.2-11b-vision-instruct@cf/meta/llama-3.2-11b-vision-instruct |
— | 128,000 | 1 | $0.051168/1M | $0.71318/1M | prepaid |
meta-llama/llama-3.2-1b-instruct@cf/meta/llama-3.2-1b-instruct |
— | 60,000 | 1 | $0.028485/1M | $0.212055/1M | prepaid |
meta-llama/llama-3.2-3b-instructMeta: Llama 3.2 3B Instruct |
— | 131,072 | 1 | $0.0537/1M | $0.353425/1M | prepaid |
meta-llama/llama-3.3-70b-instruct-fp8-fast@cf/meta/llama-3.3-70b-instruct-fp8-fast |
— | 24,000 | 1 | $0.309115/1M | $2.376915/1M | prepaid |
meta-llama/llama-4-scout-17b-16e-instructLlama 4 Scout Instruct |
— | 131,072 | 1 | $0.28485/1M | $0.89675/1M | prepaid |
meta-llama/llama-guard-3-8b@cf/meta/llama-guard-3-8b |
— | 131,072 | 1 | $0.51062/1M | $0.03165/1M | prepaid |
mistralai/mistral-small-3.1-24b-instruct@cf/mistralai/mistral-small-3.1-24b-instruct |
— | 128,000 | 1 | $0.370305/1M | $0.585525/1M | prepaid |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 119#23 | 262,144 | 1 | $1.00225/1M | $4.22/1M | prepaid |
moonshotai/kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code |
IQ 118#28 | 262,144 | 1 | $1.00225/1M | $4.22/1M | prepaid |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 123#16 | 1,048,576 | 1 | $3.165/1M | $15.825/1M | prepaid |
nvidia/nemotron-3-120b-a12b@cf/nvidia/nemotron-3-120b-a12b |
— | 256,000 | 1 | $0.5275/1M | $1.5825/1M | prepaid |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#61 | 131,072 | 1 | $0.36925/1M | $0.79125/1M | prepaid |
openai/gpt-oss-20bOpenAI: gpt-oss-20b |
IQ 100#77 | 131,072 | 1 | $0.211/1M | $0.3165/1M | prepaid |
qwen/qwen2.5-coder-32b-instruct@cf/qwen/qwen2.5-coder-32b-instruct |
— | 32,768 | 1 | $0.6963/1M | $1.055/1M | prepaid |
qwen/qwen3-30b-a3b-fp8Qwen3 30B A3B |
— | 40,960 | 1 | $0.0537/1M | $0.353425/1M | prepaid |
qwen/qwq-32b@cf/qwen/qwq-32b |
— | 24,000 | 1 | $0.6963/1M | $1.055/1M | prepaid |
z-ai/glm-4.7-flashZ.ai: GLM 4.7 Flash |
— | 202,752 | 1 | $0.063828/1M | $0.422/1M | prepaid |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#19 | 1,048,576 | 1 | $1.477/1M | $4.642/1M | prepaid |
Questions
Does Cloudflare Workers AI have zero data retention?
TrustedRouter does not currently mark Cloudflare Workers AI as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Cloudflare Workers AI end-to-end encrypted?
TrustedRouter does not currently mark Cloudflare Workers AI as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Cloudflare Workers AI models are available through TrustedRouter?
This page currently lists 24 public Cloudflare Workers AI models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.