8Router· port 8080· gateway· connected OpenAI-compatible
Endpoint
API endpoint configuration
localhost:8080/v1
Connected

API Endpoint

Local http://localhost:8080/v1
Public http://5.223.60.79/v1 Active
Require API key is disabled — your endpoint is publicly accessible without authentication. Enable →
Enable API key authentication
Require API key for requests to your endpoint
Allow dashboard access via public IP
Dashboard is accessible at http://5.223.60.79/8router

Token Saver

Make LLM responses terse to save output tokens. Stackable with RTK compression.
0
Disabled — Normal responses
0:Off1:Mild2:Med3:Aggro4:Xtreme5:Max
Compression Stats
Tokens Saved Today
0
% Saved
0%
Cost Saved Est.
$0.00
Total Compressed
0
Before Compression
0
After Compression
0
Total Requests
0
Input Tokens
0
Output Tokens
0
Total Tokens
0
Est. Cost
$0.00
Avg Latency
0ms
Error Rate
0%
Fallbacks
0

Daily Requests (Last 7 Days)

Top Provider
-
Top Model
-

Recent Requests

TimeProviderModelTokensLatencyStatus
No requests yet
Quota Tracker
Monitor provider quotas and usage limits

Budget Controls

Providers
All connected AI providers and their status
ProviderTierHealthLatencyAPI KeysRequestsTokensErrorsLast Error
Model Combos
Fallback chains — use a single model name that auto-routes through provider tiers
Settings
Configure 8Router behavior
RTK Token Compression
Compress tool output (git diff, grep, tree) to save tokens
Circuit Breaker
Auto-disable failing providers after consecutive errors
SSE Streaming
Enable streaming responses for chat completions
Multi-Key Rotation
Round-robin across multiple API keys per provider
Auto-Fallback
Automatically try next provider on failure
Token Compression
Model & Routing
Logging

System Info

Connections
SQLite-backed connection tracking with backoff and cost
IDProviderNameAuthStatusHealthBackoffRetryNext RetryRequestsTokensCost
CLI Tools
Configure and monitor AI CLI assistants connected to 8Router
API Keys
Manage virtual API keys for endpoint authentication
KeyNameCreatedLast UsedRequestsStatus
Request Logs
Live request log with method, path, status, and latency
No logs yet. Send a request to see activity here.
Playground
Test prompts and explore provider responses in real time
Temp 0.7
Max tokens
Stream
Provider
Tokens
Latency
Cost
Fallback
Model
Response
Response will appear here...