OpenAI

GPT-6 Luna Decisions

Available
gpt-6-luna-decisions

Call gpt-6-luna-decisions on Lazu for $0.12 per million input tokens and $0.00 per million output tokens.

gpt-6-luna served through the Decisions endpoint for single-call structured judgments.

Get an API key
Copy page
Context8k
InputText · Image
Outputdecision
Endpoints/v1/decisions

Prices and lanes

USD per million tokens. Availability covers the last 7 days, 2 hours per bar.

Lane InputOutputCache readCache write 5m 7-day availability
OpenAI official price $0.10 ——— —
Stable $0.12 $0.00$0.00$0.00 100.0%

Prices checked 2026-11-03 19:03 UTC · How to choose a lane · gpt-6-luna-decisions.json · gpt-6-luna-decisions.md

Capabilities

Vision
Unsupported parameters
stream, tools, temperature, safety_identifier — leave it out of the request; this model does not accept it

Example request

POST /v1/decisions
curl -X POST https://api.lazu.ai/v1/decisions \
  -H "Authorization: Bearer $LAZU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-luna-decisions"
  }'

Any OpenAI SDK works too: set base_url to https://api.lazu.ai/v1. Full integration docs

Questions

What is the difference between the stable and agent lanes?

The stable lane runs on each maker's official API, is billed at the list price, has the highest availability and suits every use. The agent lane runs on third-party subscription pools that serve the model through its official client, not the official API. It costs far less, but availability varies, a failed request does not fall back to the stable lane, and the pool adds its own preset context. So use it only inside the matching agent tool: Claude models in Claude Code, GPT models in Codex, Gemini models in Antigravity. For your own code, or anywhere the output must be controlled exactly, use the stable lane. Both lanes work with the same key, and each key picks the lane per model.

Can I call gpt-6-luna-decisions with the OpenAI SDK?

Yes. Point the SDK's base URL at https://api.lazu.ai/v1 and use gpt-6-luna-decisions as the model name. The native decisions endpoint /v1/decisions works as well.

How is it billed?

Per token actually used — input, output and cache — deducted from your wallet balance. There is no monthly fee, and every request shows up itemized in your usage log.

Same family

Get a key and call it now

Start free Read the docs