AI Management
LLM relay, proxy, round-robin & real-time stats
Cost this month: $1,247.32
8
Active Agents
6
LLM Providers
12.4M
Tokens Today
3
Proxy Routes
RR
Round-Robin ON
LLM Providers
Strategy:|Failover:|Weight:
Open
Anth
Goog
Loca
O
OpenAIConnected
8 models2.4M today$24.15p50: 340ms99.9% uptimeweight: 40
#1
A
AnthropicConnected● LIVE
4 models1.8M today$18.72p50: 520ms99.8% uptimeweight: 30
claude-sonnet-4-20250514847 tok512ms2s ago
#2
G
Google AIConnected
3 models0.6M today$4.80p50: 410ms99.7% uptimeweight: 20
#3
L
Local (Ollama)Connected
12 models7.6M today$0.00p50: 1.2s98.5% uptimeweight: 10
llama3.2:3b2048 tok1.1s15s ago
#4
Proxy / Relay Endpoints
/v1/chat/completionsActive
Upstream: http://localhost:8080/v11247 hits todayp50 420ms4 models routed
/v1/embeddingsActive
Upstream: http://localhost:8080/v1892 hits todayp50 180ms2 models routed
/v1/completionsInactive
Upstream: http://localhost:9090/v10 hits todayp50 —1 models routed
Real-Time LLM Request Log
Live
11:32:41POST/v1/chat/completionsAnthropicclaude-sonnet-4200512ms847 tok
11:32:38POST/v1/chat/completionsOpenAIgpt-4o200340ms1240 tok
11:32:30POST/v1/embeddingsOpenAItext-embedding-3200180ms4096 tok
11:32:15POST/v1/chat/completionsGoogle AIgemini-1.5-pro200410ms623 tok
11:32:10POST/v1/chat/completionsLocal (Ollama)llama3.2:3b4290ms0 tok
11:31:55POST/v1/chat/completionsAnthropicclaude-haiku200280ms512 tok
11:31:42POST/v1/chat/completionsOpenAIgpt-4o-mini200210ms1560 tok
11:31:30POST/v1/completionsLocal (Ollama)codellama:7b5035000ms0 tok
Quick Access
Provider Settings
Configure LLM providers and API keys
Usage Analytics
Token usage, cost breakdown, trends