Run machine learning models, powered by serverless GPUs, on Cloudflare's global network. Inference platform · OpenAI-compatible API · Edge · Low Latency · Open Source · Serverless

Intelligence vs Price

Best value among Cloudflare models on this chart: Llama 2 7B Chat · Mistral 7B Instruct. Hover any dot for full pricing, or click a creator in the legend to isolate.

Cloudflare models

3 models, 3 with pricing
Input/1M
to
Output/1M
to
Model
Creator
Input Price, $
Output Price, $
Context
Max Output
Inference Providers
Intelligence
Coding
Llama 2 7B ChatMeta logoMeta0.0500.1504K4Kcompare (4)9.7#1N/A
Mistral 7B InstructMistral AI logoMistral AI0.0100.100127K16Kcompare (9)7.4#2N/A
Code Llama 7B InstructMeta logoMeta0.2000.20016K16Kcompare (3)N/AN/A