Skip to main content
LLM gateways and routers

Cloudflare AI Gateway

Hosted proxy on Cloudflare's network between an application and AI model providers. It adds analytics, logging, caching, rate limiting, retries, fallbacks and spend limits, reached through provider-specific endpoints or an OpenAI-compatible unified endpoint.

Pricing model
Usage-based
Free tier
Yes
Self-hostable
No
Open source
No

Cloudflare AI Gateway works with 15 of the LLM providers we track

Each is documented in Cloudflare AI Gateway's own docs, shown with its lowest current rate from the prices we track, per 1M input tokens. Cloudflare AI Gateway may support providers we don't track; its documentation (opens in a new tab) has the full list.

LLM providers that Cloudflare AI Gateway works with
ProviderLive price
Amazon AWSSetup docs ↗ for Amazon AWS (opens in a new tab)from $0.018/1M input53 models
AnthropicSetup docs ↗ for Anthropic (opens in a new tab)from $0.100/1M input15 models
BasetenSetup docs ↗ for Baseten (opens in a new tab)from $0.100/1M input11 models
CerebrasSetup docs ↗ for Cerebras (opens in a new tab)from $0.990/1M input1 model
CohereSetup docs ↗ for Cohere (opens in a new tab)from $0.037/1M input2 models
DeepSeekSetup docs ↗ for DeepSeek (opens in a new tab)from $0.300/1M input2 models
Google CloudSetup docs ↗ for Google Cloud (opens in a new tab)from $0.037/1M input15 models
GroqSetup docs ↗ for Groq (opens in a new tab)from $0.075/1M input3 models
Microsoft AzureSetup docs ↗ for Microsoft Azure (opens in a new tab)from $0.150/1M input9 models
Mistral AISetup docs ↗ for Mistral AI (opens in a new tab)from $0.100/1M input9 models
OpenAISetup docs ↗ for OpenAI (opens in a new tab)from $0.025/1M input22 models
OpenRouterSetup docs ↗ for OpenRouter (opens in a new tab)from $0.015/1M input213 models
PerplexitySetup docs ↗ for Perplexity (opens in a new tab)from $0.150/1M input5 models
ReplicateSetup docs ↗ for Replicate (opens in a new tab)—
xAISetup docs ↗ for xAI (opens in a new tab)from $1.00/1M input5 models