---
title: "OpenAI Patches GPT-6 Sol and Luna's Silent Image Understanding Bug"
subtitle: "OpenAI patched an image encoding bug that was quietly hurting vision quality on GPT-6 Sol and GPT-6 Luna across the API, Codex, and computer use."
url: "https://alphasignal.ai/news/openai-patches-gpt-6-sol-and-luna-s-silent-image-understanding-bug"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "OpenAI Developers"
company_url: "https://alphasignal.ai/company/openaidevs"
published: "2026-09-27T16:50:19.000Z"
updated: "2026-09-27T16:58:56.293Z"
type: "News"
topics:
  - "Api"
  - "Image"
subtopics:
  - "Vision Language"
  - "Object Detection"
upvotes: 6281
read_time: "3 min"
source_url: "https://developers.openai.com/api/docs/changelog#:~:text=Fixed%20a%20bug%20in%20image%20encoding"
comments: 0
---

# OpenAI Patches GPT-6 Sol and Luna's Silent Image Understanding Bug

> OpenAI patched an image encoding bug that was quietly hurting vision quality on GPT-6 Sol and GPT-6 Luna across the API, Codex, and computer use.

OpenAI has fixed an image encoding bug that degraded visual understanding in [GPT-6 Sol](https://developers.openai.com/api/docs/models/gpt-6-sol) and GPT-6 Luna, two multimodal reasoning models released days before the patch. The server-side update is live in the API and Codex, including computer-use workflows.

OpenAI’s [API changelog](https://developers.openai.com/api/docs/changelog) does not quantify the regression or provide benchmark deltas. Requests still completed, which left developers with plausible answers and lower-than-expected evaluation scores instead of explicit errors. Teams that tested either model with images should rerun those evaluations.

## Why plausible answers slipped through

The image encoder converts pixels into internal representations that the model can analyze. A defect at this stage can omit or distort visual details before reasoning begins, causing the model to misread text, objects, layouts, or interface controls while still producing a fluent response.

OpenAI has corrected a similar defect before. A March update fixed a small encoder bug affecting `input_image` inputs in GPT-5.4, and the company said some image-understanding use cases could improve automatically.

## One encoder, several surfaces

- **GPT-6 Sol (`gpt-6-sol`):** the higher-capability tier.
- **GPT-6 Luna (`gpt-6-luna`):** the lower-cost, high-volume tier.
- **Responses and Chat Completions APIs:** image requests sent to either model.
- **Codex and computer use:** workflows that inspect screenshots or other images.

Computer-use agents depend on accurate screenshot interpretation for every action. Distorted visual features can lead an agent to select the wrong control, misread a form field, enter text in the wrong place, or incorrectly decide that a task has finished.

## Server-side patch, unchanged prices

The fix requires no code changes or model-version migration. New requests use the corrected path automatically, while outputs generated before the patch remain unchanged. Application-level caches, stored responses, and evaluation records from affected runs require separate review.

Standard API pricing per 1 million tokens for prompts up to 272,000 input tokens

| Model | Input | Cached input | Output |
| --- | --- | --- | --- |
| GPT-6 Sol | $2.00 | $0.20 | $10.00 |
| GPT-6 Luna | $0.10 | $0.01 | $0.50 |

## Rerun the evidence

The same model IDs now use a corrected image path, so pre-fix and post-fix evaluations reflect different serving behavior. Keep prompts, images, tools, sampling settings, and scoring methods constant when comparing results, and record run timestamps alongside the changelog entry.

1. **Repeat vision evaluations.** Rerun tests conducted between the models’ launch and the patch, then compare accuracy and failure categories.
2. **Retry visual agent failures.** Revisit Codex and computer-use runs involving misread controls, screenshots, text, or page state.
3. **Review stored results.** Inspect application-level caches and saved outputs produced before the fix because the patch cannot revise completed responses.
4. **Reconsider model-selection decisions.** Collect corrected multimodal results before switching models based on earlier visual performance.

## Sources

- [OpenAI API Changelog](https://developers.openai.com/api/docs/changelog)
- [GPT-6 Sol model page](https://developers.openai.com/api/docs/models/gpt-6-sol)
- [OpenAI Developers on X](https://x.com/openaidevs/status/2104252306447544447)