Hyperion
Hyperion
HomeFeaturesPerformancePricingBlogDocs
Join the beta
GitHub
IntroductionQuick StartArchitecture
CachingSmart RoutingBudgets & LimitsAuto Model Selection
QuickstartConfiguration
Overview
OpenAIAnthropicDeepSeekGoogle GeminiOllama (Local LLMs)
Environment VariablesDocker ComposeProduction Checklist
BenchmarksRun Your OwnGateway Comparison
Model Providers

Model Index

Hyperion provides a unified interface to the world's leading AI models. Whether you're using cloud-scale giants or local open-source models, Hyperion layers enterprise-grade caching and governance over every request.

01
OpenAI

The gold standard for reasoning and creative output. Optimized for GPT-4o and GPT-4o mini via Hyperion Caching.

02
Anthropic

Enterprise-grade safety and industry-leading context windows. Full protocol parity for Claude 3.5 Sonnet.

03
DeepSeek

High-efficiency, cost-optimized intelligence. Hyperion supercharges DeepSeek with stability and semantic caching.

04
Google Gemini

Massive context capabilities and multi-modal proficiency. Optimized long-context retrieval for Gemini 1.5 Pro.

05
Ollama

Production-ready local open-source models. Governance, RBAC, and observability for your on-prem compute.

Unified Access

All providers integrated via Hyperion benefit from our Universal Schema. Switch between providers by changing a single parameter in your config while maintaining identical observability and caching logic.

Last updated: Feb 22, 2026
Edit on GitHubSupport
Hyperion
Hyperion

Empowering the next generation of AI infrastructure. Microsecond gateway latency, enterprise-grade security.

Product

  • Features
  • Semantic Caching
  • Routing
  • Security
  • Pricing

Resources

  • AI Gateway
  • LLM Gateway
  • Performance

Use Cases

  • All Use Cases
  • Chatbots
  • SaaS
  • Healthcare
  • Internal Tools

Company

  • About Us
  • Contact Us
  • Blog
  • FAQs
  • Privacy

© 2026 Hyperion Inc. Built for the future of AI.

Deploy Anywhere