OpenAI GPT-5.6
OpenAI powers optional Concierge chat through the Chat Completions API — GPT-5.6 Terra (balanced) and GPT-5.6 Luna (fast) on the same x402 USDC / TCX pay-per-call stack. Pick a model in Executive Lounge or pass agentModel on POST /api/concierge.
Status: Live on conc-exe.xyz · Executive Lounge model picker + API
API base: https://api.openai.com/v1/chat/completions
Operator keys: platform.openai.com/api-keys ↗
Concierge adapter: backend/concierge-api/concierge-openai.ts
Settlement: 0.1 USDC per chat (or TCX via Token Pay) — unchanged from other Concierge models.
How it works
- Operator sets
OPENAI_API_KEYon the Concierge deployment. - Client selects
gpt-5.6-terraorgpt-5.6-lunain Lounge, or sendsagentModelin the chat body. - Concierge calls OpenAI Chat Completions with the mapped model id.
- User pays x402 USDC (Solana, Base, or Arbitrum) or TCX — consumers do not need an OpenAI key.
- On API error or missing operator key, Concierge falls back to Gemini (
modelFallback: true).
Image, enhance, and trading-plan modes always use Gemini. GPT-5.6 models apply to mode: "chat" only.
Model map
agentModel | OpenAI model id | Lounge label |
|---|---|---|
gpt-5.6-terra | gpt-5.6-terra | GPT-5.6 Terra |
gpt-5.6-luna | gpt-5.6-luna | GPT-5.6 Luna |
Aliases: openai, gpt, terra, luna. Registry: concierge-llm-models.ts.
Configuration (operators)
| Variable | Purpose |
|---|---|
OPENAI_API_KEY | OpenAI API key — required for GPT models on your deploy |
OPENAI_API_BASE_URL | Override API URL (default https://api.openai.com/v1) |
See repo docs/configuration.md and .env.example.
Example API call
pay curl https://conc-exe.xyz/api/concierge \
-H "Content-Type: application/json" \
-d '{
"mode": "chat",
"message": "Summarize BTC vs ETH momentum this week.",
"history": [],
"agentModel": "gpt-5.6-terra"
}'Swap agentModel to gpt-5.6-luna for the fast tier. Payment is x402 USDC or TCX — same as Gemini and Claude chat.
Related
Concierge Agent × OpenAI · openai.com