CPEN RouterOpenAI-compatible routing with live price caps

cpen/middle

Extraction, classification, support chat, app assistants.

availableTry in playground

Pricingper 1M tokens

Min$0.05

Max$0.35

Default cap$0.35 cap

RoutingMiddle

Model family: GPT mini / Gemini flash class
Candidates: 107 internal candidates
RPM cap: 120 RPM
Strategy: Best intelligence-adjusted cost inside the ceiling.
Fallback: Fallback within Middle first, then obey escalation policy.

QuickstartPOST /v1/chat/completions

curl https://cpenrouter.space/v1/chat/completions \
  -H "authorization: Bearer cpen_live_..." \
  -H "content-type: application/json" \
  -d '{
    "model": "cpen/middle",
    "messages": [{"role": "user", "content": "normalize this row"}],
    "routing": {
      "currency": "USD",
      "min_total_per_1m": "0.05",
      "max_total_per_1m": "0.35",
      "rpm_cap": 120,
      "strategy": "balanced",
      "continuity_mode": "temporary_escalation",
      "allow_temporary_high_price": true
    }
  }'

Policy controlsprice sensitive routing

Control	Default	Effect
Minimum price	$0.05	Avoid suspiciously cheap routes below the quality floor.
Maximum price	$0.35	Reject requests when no internal route fits the cap.
Continuity	Optional escalation	Recommended default for keeping quality and price stable.