Workspace Overview
Real-time inference analytics, token metrics, and API gateway health.
Total Prompt Inferences
1,428,920+14.2%
Active Tokens Used
742,000+8.1%
Avg Request Latency
248 ms-12.4%
API Cost This Month
$38.42+4.5%
Inference & Bandwidth Velocity
Live Edge StreamReal-time throughput metrics across global cluster
Token Usage by Model
Aggregated consumption over past 30 days
Claude 3.7 Sonnet (Reasoning)410,000 tokens (55%)
DeepSeek V3 (High-Speed Coding)220,000 tokens (30%)
GPT-4o Mini (Embeddings & Routing)112,000 tokens (15%)
Active API Keys
Generate secret keys for backend SDK pipelines and serverless webhooks.
nex_live_••••••••••••••••
Recent Gateway Requests
Auto-refreshing (every 5s)| Request ID | Model | Endpoint | Tokens | Latency | Status | Timestamp |
|---|---|---|---|---|---|---|
| req_8192a | Claude 3.7 Sonnet | /v1/chat/completions | 842 | 210ms | 200 OK | 2 mins ago |
| req_8192b | DeepSeek V3 | /v1/agents/stream | 1240 | 185ms | 200 OK | 5 mins ago |
| req_8192c | GPT-4o Reasoning | /v1/embeddings | 320 | 95ms | 200 OK | 12 mins ago |
| req_8192d | Claude 3.7 Sonnet | /v1/chat/completions | 650 | 230ms | 200 OK | 24 mins ago |