---
id: "openai/gpt-6-luna-pro"
also: ["openai/gpt-6-luna-pro-20260922"]
card_usd_per_m: "0.1 in, 0.5 out, at openai"
cheapest_list_usd_per_m: "0.05 in, 0.25 out, at openai/flex on openrouter"
cheapest_effective_usd_per_m: "0.0199 in, 0.2507 out, at openai/flex on openrouter"
context: 1050000
max_output: 128000
input: ["file", "image", "text"]
output: ["text"]
released: "2026-09-22"
reasoning: ["max", "xhigh", "high", "medium", "low", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "structured_outputs", "tool_choice", "tools", "verbosity"]
endpoints: 6
gateways: "openrouter (6)"
no_training: 6
trains: 0
retains_prompts: 3
---
# OpenAI: GPT-6 Luna Pro

GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...