About
What is gateway?
Gateway is an open-source AI Gateway designed for fast, reliable, and secure routing to over 1600 language, vision, audio, and image models. It offers a lightweight, enterprise-ready solution that integrates with any language model in under 2 minutes, boasting blazing fast latency (<1ms) and a tiny footprint (122kb). The tool is battle-tested, having processed over 10 billion tokens daily, and provides enterprise-grade security, scalability, and custom deployments. Key functionalities include automatic retries and fallbacks to prevent downtimes, load balancing for high availability, and conditional routing for scaling AI applications. It also features robust guardrails to protect AI deployments, multi-modal capabilities, and integrations for agentic workflows. The enterprise version offers advanced capabilities like org management, governance, and enhanced security.
Best used for
Ideal for developers and startup founders who need to integrate with various LLMs quickly, ensure high availability for AI applications, and protect deployments with security and accuracy standards. Especially valuable for those requiring blazing fast routing and robust guardrails across multiple AI models.
Common actions
open-sourceautomated workflowdeepfakeworkflowscollaborationlow-code/no-codeface swapping"AI Agents"github copilot
Capabilities
Key features
- Route to 1600+ AI models
- Integrated AI guardrails
- Automatic retries and fallbacks
- Load balancing
- Multi-modal capabilities
- Secure key management
- Smart caching
Target Audience
developerstartup founderproduct manager
Integrations
openaiazure-openaianyscalegoogle-geminianthropiccoheretogether-aiperplexity+ 13 more
Pricing & Plans
Open Source ยท Freemium ยท Enterprise
FAQs
What is the difference between the open-source and enterprise versions of Gateway?
The open-source version provides core AI Gateway functionalities like routing, retries, and guardrails. The enterprise version offers advanced capabilities such as org management, governance, enhanced security, PII redaction, and compliance (SOC2, HIPAA, GDPR), along with professional support for private deployments.
How does Gateway ensure reliability and prevent downtimes for AI applications?
Gateway ensures reliability through automatic retries with exponential backoff for failed requests and fallbacks to alternative providers or models. It also supports load balancing across multiple API keys or AI providers to maintain high availability and optimal performance for your AI applications.
Can I use Gateway with my existing AI frameworks and models?
Yes, Gateway is designed for broad compatibility. It supports over 200 LLMs and integrates seamlessly with popular agent frameworks like Autogen, CrewAI, LangChain, and LlamaIndex. It also works with various language, vision, audio, and image models, all accessible via a unified API.