NexusComputeBETA
Back to Endpoints
Cold — first request slower
gpt-4o-mini

GPT test

GPT-4o Mini · testing · US East (N. Virginia)

$0.6000
per 1k tokens
Status
Cold
Cold Start
~4.8s
Total Calls
0
Tokens Served
0.0k
Quick Start
curl
curl -X POST /api/endpoints/2/infer \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"prompt": "Hello, world!", "maxTokens": 256}'

Endpoint URL: /api/endpoints/2/infer

Test Console
Hardware
GPU
NVIDIA A100
Count
1×
VRAM
80 GB
Uptime
99.90%
Location
US East (N. Virginia)
Provider
testing
Model
Model
GPT-4o Mini
Provider
OpenAI
Context
128,000 tokens
Provider Rate$0.5000/1k
Platform Fee$0.1000/1k
Total$0.6000/1k
Jobs are queued and dispatched to the provider's agent. Cold starts add ~4.8s; warm endpoints respond faster. The test console polls until your job completes.