Inference console / prod-eu-west
Requests · 24h
8.42M
12.4% vs. last 24h
P99 latency
312ms
18ms slower than median
Error rate
0.08%
0.02 improvement
Tokens · 24h
1.97B
7.1% streaming + batch
Endpoint health 42 routes · sorted by traffic
All regions
eu-west
eu-north
us-east
Endpoint Requests · 1h P99 Errors Status Actions
POST /v3/chat/completions 412,308 208ms 0.04% Healthy
STREAM /v3/chat/completions:stream 287,140 412ms 0.12% Degraded
POST /v3/embeddings 196,512 94ms 0.01% Healthy
GET /v3/models 88,904 42ms 0.00% Healthy
POST /v3/fine-tunes 12,488 1.04s 0.34% Failing
DELETE /v3/sessions/{id} 9,221 61ms 0.07% Watch