Advanced Routing Controls

Data Privacy Controls

Control how your data is handled by setting privacy parameters on each request. KairosRoute filters out providers that don't meet your requirements.

curl https://api.kairosroute.com/v1/chat/completions \
  -H "Authorization: Bearer kr-your-key" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Analyze this PII data"}],
    "data_collection": "deny",
    "zdr": true
  }'

Performance Thresholds

KairosRoute tracks real-time latency and throughput per provider over a rolling 5-minute window. Set thresholds to automatically skip underperforming providers.

// Route to fast providers only (< 1 second P75 latency)
{
  "model": "auto",
  "messages": [...],
  "preferred_max_latency": 1000,
  "preferred_min_throughput": 50
}

Performance data is available at GET /api/v1/performance. Providers with fewer than 3 recent samples are given the benefit of the doubt.

Quantization Filtering

Some providers serve quantized (compressed) versions of models for faster/cheaper inference. Control the precision level of models you're routed to.

// Only accept FP8 or higher precision models
{
  "model": "auto",
  "messages": [...],
  "min_quantization": "fp8"
}

// Prefer cheaper quantized models (int8 or lower)
{
  "model": "auto",
  "messages": [...],
  "max_quantization": "int8"
}

Context Compression

When a conversation exceeds a model's context window, KairosRoute applies middle-out truncation instead of returning an error. System messages and recent messages are preserved; older middle messages are dropped with a truncation notice.

Bypass the classifier

kr-auto runs a task classifier on every request to pick the cheapest model that clears the per-task quality bar. If you'd rather route deterministically on your own guardrails, you can turn it off — per key, or per request.