AI Gateway

Set up the AI Gateway from scratch: add a provider key, create an endpoint, test it, and start routing requests.

Monitor LLM usage, costs, and guardrail activity across all providers.

Configure LLM provider endpoints with model selection, API keys, and system prompts.

Test endpoints with an interactive chat interface before routing production traffic.

Configure PII detection and content filtering rules to protect AI requests.

Manage API keys, budget limits, and guardrail configuration.

Generate API keys for developers to access the gateway with any OpenAI-compatible SDK.

View, filter, and inspect every request that flows through the AI Gateway.

Create versioned prompt templates with variables, test them with streaming responses, and bind them to endpoints.

Browse the full LLM model catalog, compare features side by side, and estimate monthly costs across providers.

Understand what the MCP Gateway does, how it works, and why you need it for agent governance.

Register backend MCP servers, configure authentication, and monitor health status.

View discovered tools, assign risk levels, and enable approval requirements.

Create scoped API keys for AI agents with tool ACLs, rate limits, and expiration.

Review tool invocation history with stats, charts, filters and pagination.

Review and decide on pending tool execution requests that need human sign-off.

Configure PII detection, content filtering, and prompt injection rules for MCP tool inputs.