GPT-6 Luna API on KeyoAPI — High-Volume Cheap Chat
GPT-6 Luna on KeyoAPI is the cheap high-volume lane of the GPT-6 family.
Overview
GPT-6 Luna on KeyoAPI is the cheap high-volume lane of the GPT-6 family. Indicative rates are about $0.03 / $0.15 per 1M in/out — confirm live on /pricing/gpt-6-luna. Keep product defaults on gpt-6-sol or gpt-6-astra and route bulk traffic here so blended COGS stays intentional. Same OpenAI-compatible gateway as the rest of KeyoAPI: https://www.keyoapi.xyz/v1 with Bearer auth. No second SDK.
Quick start
Base URL: https://www.keyoapi.xyz/v1
Endpoint: POST /v1/chat/completions
Model: model=gpt-6-luna
curl https://www.keyoapi.xyz/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-6-luna","messages":[{"role":"user","content":"Hello from GPT-6 Luna"}]}'
Auth uses the same Bearer API key as chat. Full notes: Keyo docs.
FAQ
When should I use gpt-6-luna?
Use it for high-volume classification, triage, and draft paths where unit cost matters more than peak IQ. Escalate to gpt-6-sol or gpt-6-astra when quality gates fail.
How do I call it?
Set baseURL to https://www.keyoapi.xyz/v1, Authorization: Bearer YOUR_KEY, and model=gpt-6-luna on POST /v1/chat/completions.