0API
Status
Profile & Balance
Admin
@user
|
$0.00
Logout
Sign In
System Status
All Systems Operational
LIVE
Availability, response benchmarks, and active model pricing for all models.
Updated just now
Probe All Models
Refresh
Based on the last 20 automated probes per model
--
optimal
--
slow
--
down
--%
availability
·
--s
response time
Response Time & Uptime Telemetry
Live latency benchmarks in seconds. Select a provider below to inspect individual models.
Range:
LIVE
15m
1h
24h
7d
All Providers
Claude
GPT
DeepSeek
GLM
Grok
Moonshot AI
Poolside
6 providers
All
Claude
GPT
DeepSeek
GLM
Grok
Moonshot AI
Poolside
Gemini
Soon
Live Feed
Loading model telemetry...
Operational
Claude
gpt-5.6-sol
OpenAI Flagship Reasoning Engine
✕
Availability (20 Probes)
100%
Avg Latency
1.85s
Engine Specifications
Context Window:
1,000,000 tokens
Auto-Compact:
895,000 tokens
Streaming:
Native SSE
Compatibility:
OpenAI & Anthropic
Recent Health Probes (Last 20)
⚡ Probe Now
Live cURL Playground
Copy cURL
