gpt-6-luna
openaimodel ID gpt-6-luna-63%63% OFF
gpt-6-luna costs $0.037 per million input tokens and $0.185 per million output tokens through the KoRouter API — 63% below OpenAI's official rate, pay as you go with credits.
- Context window922K input tokens
- Input modalitiestext, image, file
- Output modalitiestext
Call it in one request
curl https://korouter.ai/v1/chat/completions \
-H "Authorization: Bearer sk-your-key" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6-luna",
"messages": [{ "role": "user", "content": "Hello" }]
}'gpt-6-luna answers on the OpenAI-compatible endpoint, so anything that accepts an OPENAI_BASE_URL — Codex, Cline, Continue, Aider, Open WebUI, the OpenAI SDKs — needs the base URL, a key, and this model ID. Setup guides per tool.
Replace sk-your-key with a key from the console. Model IDs are bare names — see the docs.
What a real coding session costs
Per-token price tables mislead for agentic coding. A focused two-hour Claude Code session re-sends its context on every request, so 88% of its tokens are cache reads rather than fresh input — and the cache rate, not the headline input price, decides most of the bill. Priced at gpt-6-luna's live rates, that session costs $0.06 through KoRouter, against $0.17 at OpenAI's official prices.
- Cache reads · 5M tokens$0.02
- Fresh input · 250K tokens$0.0092
- Output · 100K tokens$0.02
- Cache writes · 350K tokens$0.02
- Session total$0.06
The token mix is a stated assumption, not a measurement — change it and re-price every model in the cost calculator, or read the full worked example in what a real Claude Code session costs. Prices come from the live billing catalog.
The same session elsewhere
The same reference session, priced at each model's live KoRouter rates — the nearest options on either side of gpt-6-luna.
- deepseek-v4-flash$0.03
- deepseek-v4-flash-0731$0.03
- deepseek-v4-pro$0.12
- deepseek-v4-pro-0813$0.12
- glm-5.2$0.90
Supported parameters
More models
Prices use the live billing catalog · all models