Cloudflare Workers AI Models — Pricing & Benchmarks

40 models available · Cloudflare

Last refreshed 2026-09-30. Next refresh: weekly.

Cloudflare Workers AI hosts 40 AI models in this catalog. The lowest listed input price is Llama 3.2 1B Instruct at $0.027/1M input tokens. LLM Reference compares these models across all 97 providers.

ModelInput (per 1M)Output (per 1M)Context
Llama 3.2 1B Instruct$0.027$0.201128k
Llama 3.2 11B Vision Instruct$0.049$0.676128k
Llama 3.2 3B Instruct$0.051$0.335128k
Qwen3-30B-A3B$0.051$0.335128k
GLM-4.7 Flash$0.06$0.4198k
Gemma 4 26B A4B IT$0.1$0.3256k
gpt-oss-20b$0.2$0.3131k
Llama 4 Scout 17B-16E Instruct$0.27$0.8510m
Llama 3.3 70B Instruct (free)$0.293$2.2566k
Gemma 3 12B$0.345$0.55633k
gpt-oss-120b$0.35$0.75131k
Mistral Small 3.1 24B Instruct$0.351$0.555128k
Llama Guard 3 8B$0.484$0.038k
DeepSeek R1 Distill Qwen-32B$0.497$4.88128k
Qwen2.5-Coder-32B-Instruct$0.66$1.00128k
QwQ 32B$0.66$1.00128k
Kimi K2.6$0.95$4.00262k
BGE Base EN v1.5——512
BGE Large EN v1.5——512
BGE M3——8k
BGE Reranker Base——512
BGE Small EN v1.5——512
FLUX.1 [schnell]———
Gemma 2B Instruct——2k
Gemma 7B Instruct——8k
Granite 4.0 H Micro——131k
Hermes 2 Pro Mistral 7B——32k
Kimi K2.5——256k
Llama 2 7B Chat——4k
Llama 3 8B Instruct——8k
Llama 3.1 70B Instruct——128k
Llama 3.1 8B Instruct——128k
LLaVA 1.5 7B——4k
Mistral 7B Instruct v0.2——32k
Mistral 7B v0.1——8k
Nemotron 3 Super-120B-A12B——1.05m
Phi-2——2k
Qwen3 Embedding 0.6B——33k
SEA-LION V4 27B Instruct——128k
SQLCoder 7B 2——32k

Where else to run this

Llama Guard 3 8B on Cloudflare Workers AI
Provider setup and pricing
Llama 2 7B Chat on Cloudflare Workers AI
Provider setup and pricing
Kimi K2.6 on Cloudflare Workers AI
Provider setup and pricing
Llama Guard 3 8B on Microsoft Foundry
Alternative host
Llama 2 7B Chat on Alibaba Cloud PAI-EAS
Alternative host
Kimi K2.6 on NVIDIA NIM
Alternative host

Pricing Overview

Cheapest$0.03/1M
Most expensive$0.95/1M

About Cloudflare Workers AI

Cloudflare Workers AI is a serverless GPU inference platform enabling developers to run machine learning models on Cloudflare's global edge network. It supports diverse AI tasks including text generation, image classification, automatic speech recognition, and real-time language translation. The platform provides pay-per-use pricing and access to a curated library of open-source models from Hugging Face, enabling rapid deployment without complex infrastructure management. Key features include low-latency edge computing, streaming responses for large language models, context length customization, and the AI Gateway for monitoring, caching, and cost optimization.

Full provider profile →

Links

Dashboard Documentation Pricing