About GPT 5.6 Luna
GPT 5.6 Luna is the GPT-5.6 model optimized for cost-sensitive, high-volume workloads. It is the lowest-cost member of the GPT-5.6 family while retaining the family's token efficiency, frontend design quality, and intent understanding.
It supports configurable reasoning effort (none, low, medium, high, xhigh, and max), a pro reasoning mode for quality-first tasks, programmatic tool calling, persisted reasoning across turns, and a broad tool set including functions, web search, file search, and computer use.
| Metric | Value |
|---|---|
| Context Length | 1,050,000 tokens |
| Max Output Tokens | 128,000 tokens |
| Knowledge Cutoff | Feb 16, 2026 |
| Multilingual | Yes |
Ready to build with GPT 5.6 Luna?
Try GPT 5.6 Luna in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
bash
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "gpt-5-6-luna",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'