GPT-6 Luna is the speed-and-price tier of the GPT-6 family, positioned below GPT-6 Sol for latency-sensitive, high-concurrency workloads: chat, routing, extraction and light coding. GPT-6 family quality at nano-class prices.
FastTool Use
GPT-6 Luna is the speed-and-price tier of the GPT-6 family, positioned below GPT-6 Sol for latency-sensitive, high-concurrency workloads: chat, routing, extraction and light coding. GPT-6 family quality at nano-class prices.
Drop-in OpenAI replacement. Change only the base_url and model.
# Python -pip install openai from openai import OpenAI client = OpenAI( base_url="https://meshtok.com/v1", api_key="sk-your-MeshTok-key", ) resp = client.chat.completions.create( model="openai/gpt-6-luna", messages=[{"role":"user","content":"Hello!"}], ) print(resp.choices[0].message.content)
# cURL curl https://meshtok.com/v1/chat/completions \ -H "Authorization: Bearer sk-your-MeshTok-key" \ -H "Content-Type: application/json" \ -d '{"model":"openai/gpt-6-luna","messages":[{"role":"user","content":"Hello!"}]}'
Other models you might consider.
Frontier 3072-dim embeddings for RAG and search.
Cheap and fast 1536-dim embeddings at scale.
OpenAI’s latest frontier model.
Balanced GPT-5 for production.