Cloudflare Workers AI API Pricing
🌍 GlobalAPI price snapshot
Current Cloudflare Workers AI models and token prices
ComputeUnion currently tracks 42 Cloudflare Workers AI models, with input pricing from $0.0002 per 1M tokens. Each model detail page keeps this platform's quote separate from other available official or channel quotes so the official API versus relay cost gap can be checked directly.
Payment Methods
Cloudflare Workers AI is an AI API relay service. ComputeUnion tracks 55 price records for this platform (54 auto-scraped, 1 manually maintained). Browse the categories below to compare Cloudflare Workers AI pricing across providers.
Model Pricing on Cloudflare Workers AI
Prices per 1M tokens
LLM27 models
| Model | Input | Output | Context | Updated |
|---|---|---|---|---|
| DeepSeek R1 Distill Qwen 32B deepseek-r1-distill-qwen-32b | $0.4970 | $4.8810 | 32K | Updated 1h ago |
| DeepSeek V4 deepseek-v4 | $0.4400 | $1.3200 | 32K | Updated 1h ago |
| Gemma 3 12B gemma-3-12b | $0.3450 | $0.5560 | 128K | Updated 1h ago |
| Gemma 4 27B gemma-4-27b | $0.1000 | $0.3000 | 128K | Updated 1h ago |
| GLM-4.7 Flash glm-4-7-flash | $0.0600 | $0.4000 | 125K | Updated 1h ago |
| GLM-5 glm-5 | $0.1500 | $0.5000 | 32K | Updated 1h ago |
| Google Gemma google-gemma | — | — | 8K | Manually maintained |
| GPT OSS 120B gpt-oss-120b | $0.3500 | $0.7500 | 125K | Updated 1h ago |
| GPT OSS 20B gpt-oss-20b | $0.2000 | $0.3000 | 125K | Updated 1h ago |
| Kimi K2.5 kimi-k2-5 | $0.6000 | $3.0000 | 128K | Updated 1h ago |
| Kimi K2.6 kimi-k2-6 | $0.9500 | $4.0000 | 128K | Updated 1h ago |
| Kimi K2.7 Code kimi-k2-7-code | $0.9500 | $4.0000 | 128K | Updated 1h ago |
| Llama 3.1 70B Instruct llama-3-1-70b-instruct | $0.2930 | $2.2530 | 125K | Updated 1h ago |
| Llama 3.1 8B Instruct llama-3-1-8b-instruct | $0.0450 | $0.3840 | 125K | Updated 1h ago |
| Llama 3.2 11B Vision llama-3-2-11b-vision | $0.0490 | $0.6760 | 125K | Updated 1h ago |
| Llama 3.2 1B Instruct llama-3-2-1b-instruct | $0.0270 | $0.2010 | 125K | Updated 1h ago |
| Llama 3.2 3B Instruct llama-3-2-3b-instruct | $0.0510 | $0.3350 | 125K | Updated 1h ago |
| Llama 3.3 70B Instruct llama-3-3-70b-instruct | $0.2930 | $2.2530 | 125K | Updated 1h ago |
| Llama 3 8B Instruct llama-3-8b-instruct | $0.1230 | $0.2660 | 8K | Updated 1h ago |
| Llama 4 Scout llama-4-scout | $0.2700 | $0.8500 | 128K | Updated 1h ago |
| Mistral 7B Instruct mistral-7b-instruct | $0.1100 | $0.1900 | 32K | Updated 1h ago |
| Mistral Small 4 mistral-small-4 | $0.3510 | $0.5550 | 125K | Updated 1h ago |
| Nemotron 120B nemotron-120b | $0.5000 | $1.5000 | 125K | Updated 1h ago |
| Qwen2.5 Coder 32B qwen2-5-coder-32b | $0.6600 | $1.0000 | 125K | Updated 1h ago |
| Qwen3 30B A3B qwen3-30b-a3b | $0.0510 | $0.3350 | 125K | Updated 1h ago |
| Qwen3.8 27B (CF) qwen3-8-27b-cf | $0.4500 | $3.2000 | 125K | Updated 1h ago |
| QwQ 32B qwq-32b | $0.6600 | $1.0000 | 32K | Updated 1h ago |
audio9 models
| Model | Input | Output | Context | Updated |
|---|---|---|---|---|
| Aura 1 (CF) aura-1-cf | $0.0150 | $0.0150 | 32K | Data may be outdated |
| Aura 2 En (CF) aura-2-en-cf | $0.0300 | $0.0300 | 32K | Data may be outdated |
| Aura 2 Es (CF) aura-2-es-cf | $0.0300 | $0.0300 | 32K | Data may be outdated |
| Flux (websocket) (CF) flux-websocket-cf | $0.0077 | $0.0077 | 32K | Data may be outdated |
| Melotts (CF) melotts-cf | $0.0002 | $0.0002 | 32K | Data may be outdated |
| Nova 3 (CF) nova-3-cf | $0.0052 | $0.0052 | 32K | Data may be outdated |
| Nova 3 (websocket) (CF) nova-3-websocket-cf | $0.0092 | $0.0092 | 32K | Data may be outdated |
| Whisper (CF) whisper-cf | $0.0005 | $0.0005 | 32K | Data may be outdated |
| Whisper Large V3 Turbo (CF) whisper-large-v3-turbo-cf | $0.0005 | $0.0005 | 32K | Data may be outdated |
Embedding6 models
| Model | Input | Output | Context | Updated |
|---|---|---|---|---|
| Bge Base En V1.5 (CF) bge-base-en-v1-5-cf | $0.0670 | $0.0670 | 32K | Data may be outdated |
| Bge Large En V1.5 (CF) bge-large-en-v1-5-cf | $0.2040 | $0.2040 | 32K | Data may be outdated |
| Bge Small En V1.5 (CF) bge-small-en-v1-5-cf | $0.0200 | $0.0200 | 32K | Data may be outdated |
| Embed: BGE embed-bge | $0.0030 | $0.0030 | 32K | Data may be outdated |
| Plamo Embedding 1B (CF) plamo-embedding-1b-cf | $0.0190 | $0.0190 | 32K | Data may be outdated |
| Qwen3 qwen3 | $0.0120 | $0.0120 | 125K | Data may be outdated |
Sources and price verification method
This page lists Cloudflare Workers AI price records by model and distinguishes live-API, independently checked public-page, and maintained records. Platform identity, model availability, and pricing are separate evidence layers: official sources confirm vendor or model information, while ComputeUnion price records show currently comparable quotes. Relay model IDs, terms, refund policies, and regional availability should still be checked with the platform before purchase.
No vendor source is currently registered for automatic official-status decisions; this page only presents reviewable platform and pricing records already in the database.
FAQ
What is Cloudflare Workers AI?
Cloudflare Workers AI is an AI API relay service aggregating multi-provider access through a unified endpoint. ComputeUnion currently tracks 55 price records for this platform (54 auto-scraped, 1 manually maintained).
How does Cloudflare Workers AI pricing compare to official providers?
Cloudflare Workers AI quotes may differ from the official API, as may model IDs, regions, and service terms. Use the model links below to compare currently tracked quotes and verify current terms before purchase.
Is Cloudflare Workers AI accessible from China?
Cloudflare Workers AI is an international service — direct access from China mainland may be restricted.
Related pages