← All Models
GPT-5.6 Luna
OpenAI's most cost-efficient GPT-5.6 model, built for high-volume and latency-sensitive workloads. 1M+ token context, reasoning effort control, and native tool support.
Web Search
Code Interpreter
File Search
Specifications
| Provider | OpenAI |
| Category | Text |
| Context window | 1.1M tokens |
Pricing (Starter tier)
130.00 credits / 1M input tokens
780.00 credits / 1M output tokens
Higher tiers get volume discounts. See tiers
Quick Start
curl -N https://query.genx.sh/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-5.6-luna","messages":[{"role":"user","content":"Classify this support ticket by urgency"}],"max_tokens":1024,"stream":true}'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
prompt |
string | required | — | The input text prompt |
system_prompt |
string | optional | — | System instructions for the model |
max_tokens |
number | optional | 16384 |
Maximum tokens to generate (up to 128k) |
image_url |
string | optional | — | URL of an image to analyze |
tools |
array | optional | — | Builtin tools: web_search, code_interpreter, file_search |
reasoning_effort |
string | optional | — | Reasoning effort: none, low, medium, high, xhigh |