Skip to main content

AI Gateway

Connect to 250+ AI models using a single consistent API. Set up load balancers, automated fallbacks, caching, conditional routing, and more, seamlessly.

🌐 Universal API

Use any of the supported models with a universal API (REST and SDKs)

⏱️ Realtime API

Leverage OpenAI’s Realtime API for insights

🐀 MCP Support

Connect to Remote MCP severs, allowing you to connect external tools and data sources.

🏷️ Strict OpenAI Compliance

Ensure responses strictly adhere to the OpenAI specification

πŸ”€ Multimodal Capabilities

Use vision, audio, image generation, and more models

πŸ”‘ Virtual Keys

Manage provider access with virtual API keys

🚦 Projects

A collection of guardrail policies that you can oversee

Observability & Logs

Gain real-time insights, track key metrics, and streamline debugging with our OpenTelemetry-compliant system.

πŸ“œ Logs

Access and analyze detailed logs

πŸ•΅οΈ Tracing

Implement distributed tracing for request flows

πŸ“Š Analytics

Gain insights through comprehensive analytics

Guardrails

Enforce Real-Time LLM Behavior with 50+ state-of-the-art AI guardrails, so that you can synchronously run guardrails on your requests.

οΈπŸ€– Guardrail Policies

Implement rule-based safety checks

πŸ›‘ Guardrail Validators

Leverage AI for advanced content filtering

Agents

Natively integrate Obiguard’s gateway, guardrails, and observability suite with leading agent frameworks and take them to production.

πŸ€– Autogen

πŸ‘₯ CrewAI

πŸ”— Langchain Agents

πŸ¦™ Llama Agents

Ο† PhiData

πŸ”€ ControlFlow

πŸ•ΈοΈ LangGraph

More Resources

πŸ“‹ Contact Us

Have questions or need help? Contact the Obiguard team for support.

πŸ’¬ Commons errors & resolutions

Common errors encountered when using the Obiguard Gateway and their resolutions.