GPT-5.6 Luna
| Maker | OpenAI |
|---|---|
| Family | GPT Luna |
| Released | 2026-07-09 |
| Context | 1.1M |
| Max output | 128K |
| Open weights | Closed |
|---|---|
| Modalities | text, image, pdf → text |
| Input / 1M | $0.20 |
| Output / 1M | $1.20 |
| Cached input / 1M | $0.02 |
| Above 272K in | $0.40 / $1.80 |
|---|---|
| Review call | $0.0081 |
| Reasoning efforts | low, medium, high, xhigh |
| Hosts | OpenAI, OpenRouter |
| Model id | gpt-5.6-luna |
CodePanel's benchmark has not run GPT-5.6 Luna as a pull-request reviewer yet, so this page has no recall, false-alarm or measured-cost figures for it. The methodology explains how ranked models are scored.
The newest ranked model in the GPT Luna line is GPT-6 Luna. It caught 67% [53%–80%] of the known bugs at rank 1 of 17, with a measured review cost of $0.0028. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0081 on GPT-5.6 Luna and $0.0038 on GPT-6 Luna, so this model's call is 2.1× the cost of that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| OpenAI | gpt-5.6-luna | $0.20 | $1.20 |
Source: OpenAI pricing, Oct 16, 2026
| Version | Released | Input / 1M | Output / 1M | Context | Rank | Bugs caught |
|---|---|---|---|---|---|---|
| GPT-6 Luna | 2026-09-22 | $0.10 | $0.50 | 1.1M | #1 | 67% |
| Model | Maker | Input / 1M | Output / 1M | Review call | Context |
|---|---|---|---|---|---|
| Codestral 25.08 | Mistral | $0.30 | $0.90 | $0.01 | 128K |
| Gemini 3.1 Flash-Lite | $0.25 | $1.50 | $0.0102 | 1M | |
| DeepSeek Flash | DeepSeek | $0.30 | $1.20 | $0.0108 | 1M |
| GPT-OSS 120B (Groq) | Groq | $0.15 | $0.60 | $0.0054 | 131.1K |
Updated Oct 23, 2026