All models

GPT-6 Luna

Small, quick and nearly free.

openai/gpt-6-luna
The router's model ports
Input, 1M$0.10
Output, 1M$0.50
p50 first token290 ms
Throughput190 tok/s
Context1.05M
Uptime, 30 days · 99.97%
RouteOpenAI · primaryAzure · fallback

Call it.

The same request, any SDK. Press send to route one.

router.family R-1
CH OPENAI CURLTX
ROUTER=https://api.router.family/v1
curl $ROUTER/chat/completions \
-H "Authorization: Bearer $KEY" \
-d '{
"model": "openai/gpt-6-luna",
"messages": [{"role": "user",
"content": "gm"}]
}'
ready via OpenAI
KEY
ms p50

Pay for it in TARDI.

Per million tokens, at today's curve price.

Input137TARDI
Output684TARDI