AI Pipeline
LLM routing, embeddings and inference orchestration.
Vertex AI Embeddings
:7700Self-hosted Vertex inference for high-throughput embeddings.
— ms
response time
Vector Routing Rules
Loading data...
Embedding Metrics (7d)
| Provider | Model | Source Module | Requests 7d | Tokens 7d | Avg Latency | Cost 7d |
|---|
Cost Comparison (7d)
Qdrant runs on the VPS — no per-call cost. Cloud providers are billed per token.