C
Cloudflare Workers AI
Text
Workers AI allows you to run AI models in a serverless way, without having to worry about scaling, maintaining, or paying for unused infrastructure. You can invoke models running on GPUs on Cloudflare's network from your own code — from Workers, Pages, or anywhere via the Cloudflare API.
up
115ms
Models & Capabilities
Available Models
| Model Name | Context Window | Input Cost (1M) | Output Cost (1M) | Capabilities | |
|---|---|---|---|---|---|
cloudflare/@cf/meta/llama-2-7b-chat-fp16 | 3,072 | $1.923 | $1.923 | text | |
cloudflare/@cf/meta/llama-2-7b-chat-int8 | 2,048 | $1.923 | $1.923 | text | |
cloudflare/@cf/mistral/mistral-7b-instruct-v0.1 | 8,192 | $1.923 | $1.923 | text | |
cloudflare/@hf/thebloke/codellama-7b-instruct-awq | 4,096 | $1.923 | $1.923 | text |
Subscription Plans
Monthly plans, quota windows, weighted premium credits, and API access entitlement for this provider.
No subscription plans available yet for this provider.
Uptime History
System Status
100% Uptime
123ms Avg. Latency
30 minutes agoNow
Cost Estimator
Estimated Monthly Cost$2.8845
1,000,000@ $1.923 / 1M
010M
500,000@ $1.923 / 1M
05M