LLM Providers

Manage LLM providers via LiteLLM gateway — 100+ models supported

🟢 OpenAIactive

GPT-4oGPT-4o-miniGPT-3.5 Turbo

Calls: 45.2kAvg Latency: 1.8sCost (30d): $892Uptime: 99.9%

🟠 Anthropicactive

Claude Sonnet 4.6Claude Haiku 4.5

Calls: 23.1kAvg Latency: 2.1sCost (30d): $567Uptime: 99.8%

🔵 Googleactive

Gemini 3 ProGemini 3 Flash

Calls: 8.4kAvg Latency: 1.5sCost (30d): $234Uptime: 99.7%

⚡ Azure OpenAIactive

GPT-4o (East US)GPT-4o (West EU)

Calls: 12.8kAvg Latency: 1.6sCost (30d): $445Uptime: 99.95%

☁ AWS Bedrockconfigured

Claude 3.5 SonnetTitan

Calls: 0Avg Latency: -Cost (30d): $0Uptime: -