GatewayProviders

Gateway Providers

Gateway providers are different from tool adapters. Adapters observe developer workflows; Gateway providers give teams an optional governed path for virtual keys, provider-level budgets, audit logs, and routing analytics.

Supported provider paths

OpenAI

OpenAI can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Anthropic

Anthropic can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Google Gemini

Google Gemini can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Groq

Groq can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Mistral

Mistral can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Cohere

Cohere can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

xAI

xAI can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Perplexity

Perplexity can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Together AI

Together AI can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Fireworks AI

Fireworks AI can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

OpenRouter

OpenRouter can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Azure OpenAI

Azure OpenAI can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

AWS Bedrock

AWS Bedrock can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Vertex AI

Vertex AI can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Ollama

Ollama can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

LM Studio

LM Studio can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

LocalAI

LocalAI can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

Any OpenAI-compatible endpoint

Any OpenAI-compatible endpoint can be routed through FORG Gateway when teams need hard enforcement, provider-level budgets, and routing analytics.

When to use Gateway

Route requests through approved model classes before they reach a provider
Enforce provider budgets with virtual keys
Route work across approved compatible endpoints
Centralize audit logs for model calls that must be governed synchronously

If you only need observability, install an adapter. If you need synchronous policy checks, use Gateway.