AI Proxy Gateway API Server

v4
Auto-Refresh 60s | s
Open Admin Console

Live Console 0 / 1000 ● connecting

Config & Status
Server
StatusONLINE
Port3510
Uptime26m 41s
Admin URLhttps://100.108.242.63:3620/admin
TimezoneAsia/Kuala_Lumpur
Models
Available33
Unavailable0
Pending0
Total33
Database
Hostmysql
Userai_proxy_v4_prod
Passwordb70b●●●●●●●●
Databaseai_proxy_v4_prod
Timezone+08:00
Redis
URLredis://redis:6379
Cachev17
Ollama
Hosthttp://100.119.197.98:11434
Gemini
API KeyAIza●●●●●●●●
Groq
API Keygsk_●●●●●●●●
DeepSeek
API Keysk-1●●●●●●●●
Qdrant
Base URLhttp://qdrant:6333/collections/sihatai_docs
Health Check
IntervalBYPASS
Probe"reply ok"
Delay500ms
Async Jobs
Concurrency3
Queue Keyasync:jobs:queue
System
Console Buf1000
Token Rollup60 min
Proxy Settings
backoff_fallback_max_retries4
backoff_initial_delay_ms10000
backoff_jitter1
backoff_max_delay_ms30000
backoff_max_retries4
backoff_multiplier2
cache_ttl3600
callback_retry_delay_sec30
callback_retry_max0
default_fallback_modelgemini-3.1-flash-lite
default_modelgemini-2.5-flash-lite
global_rpd-1
global_rpm-1
global_tpd-1
global_tpm-1
request_events_retention_days30

Live Metrics Summary (counters reset on restart)

Provider RPMTPMAvg Lat (1H)Total ReqsTotal TokensErrors
OVERALL 001334ms190
GEMINI 001334ms190
groq 6/6 available probe
ModelStatusProbe Lat *Last Checked *RPMTPMLat 1HTotal ReqsTokensErrors
allam-2-7b Chat probe
AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
groq/compound Chat probe
AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
groq/compound-mini Chat probe
AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
openai/gpt-oss-120b Chat probe
AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
openai/gpt-oss-20b Chat probe
AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
qwen/qwen3.8-27b Chat probe
AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
deepseek 2/2 available probe
ModelStatusProbe Lat *Last Checked *RPMTPMLat 1HTotal ReqsTokensErrors
deepseek-flash Chat probe
AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
deepseek-v4-pro Chat probe
AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini 25/25 available probe
ModelStatusProbe Lat *Last Checked *RPMTPMLat 1HTotal ReqsTokensErrors
antigravity-preview-09-2026 Chat probe
Preview release of Antigravity Agent (09-2026)
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-2.5-flash Chat probe
Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1…
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-2.5-flash-lite Chat probe
Stable version of Gemini 2.5 Flash-Lite, released in July of 2025
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-2.5-pro Chat probe
Stable release (June 17th, 2025) of Gemini 2.5 Pro
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3-flash-preview Chat probe
Gemini 3 Flash Preview
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3.1-flash-lite Chat probe
Gemini 3.1 Flash Lite
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3.1-flash-lite-image Vision probe
Gemini 3.1 Flash Lite Image.
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3.1-flash-lite-preview Chat probe
Gemini 3.1 Flash Lite Preview
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3.1-pro-preview Chat probe
Gemini 3.1 Pro Preview
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3.1-pro-preview-customtools Chat probe
Gemini 3.1 Pro Preview optimized for custom tool usage
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3.5-flash Chat probe
Gemini 3.5 Flash
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3.5-flash-lite Chat probe
Gemini 3.5 Flash Lite
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3.5-transcribe Chat probe
Gemini 3.5 Transcribe
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3.6-flash Chat probe
Gemini 3.6 Flash
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3.7-flash Chat probe
Gemini 3.7 Flash
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-3.8-flash Chat probe
Gemini 3.8 Flash
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-flash-latest Chat probe
Latest release of Gemini Flash
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-flash-lite-latest Chat probe
Latest release of Gemini Flash-Lite
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-omni-1.1-flash Chat probe
Gemini Omni 1.1 Flash
AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-omni-flash-preview Chat probe
Gemini Omni Flash Preview
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-pro-latest Chat probe
Latest release of Gemini Pro
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemini-robotics-er-2-preview Robotics probe
Gemini Robotics-ER 2 Preview
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemma-4-26b-a4b-it Chat probe
Gemma 4 26B A4B IT
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
gemma-4-31b-it Chat probe
Gemma 4 31B IT
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
lyria-3.5 Audio probe
Music Generation model
 AVAILABLE — 2026-09-20 17:33:42 0 0 — — — 0
* Probe Lat / Last Checked reflect the most recent active health check probe (probe text: reply ok, inter-probe delay: 500ms). ⚠ Bypass mode active (MODEL_HEALTH_CHECK_INTERVAL_SEC=-1): no probes are performed at startup or on a schedule. Probe Lat shows — and Last Checked shows the server start time for all models. Status only changes to unavailable reactively when a POST /api/generate call fails (excluding 429 rate-limit errors).
API Reference
Full endpoint contracts — request/response shapes, parameters, error codes
View API Docs
Last updated: 2026-09-20 18:00:16 Auto-refreshes every 60s — configurable above  ·  API Reference © 2026 ME-Tech Solution Sdn Bhd · All rights reserved