GPT-4o mini can generate images.

Is it true that GPT-4o mini can generate images?

Partly. The retrieved items only partially address the claim: one study using GPT-4o mini in a text-to-image prompt-stealing pipeline suggests it can be involved in reproducing images, while a reference article and two studies describe GPT-4o mini as a text or vision-input model and attribute image generation to GPT-4o-based GPT Image 1. None directly settles whether GPT-4o mini itself can generate images.

Verdict: CONTESTED PARTIAL · 1 source for, 3 against · Last checked 3 Oct 2026

The private library was unavailable for some searches in this check. Missing library results are not evidence against the claim.

Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach. (2025). doi.org. https://doi.org/10.18653/v1/2025.findings-acl.868

GPT-4o. (n.d.). en.wikipedia.org. https://en.wikipedia.org/wiki/GPT-4o

Cirkel, L., Lechner, F., Henk, L., Krusche, M., Hirsch, M., Hertl, M., Kuhn, S., & Knitza, J. (2025). Large language models for dermatological image interpretation – a comparative study. doi.org. https://doi.org/10.1515/dx-2025-0014

Dangi, D. B., Dangi, B. B., & Steinbock, O. (2025). Evaluation of GPT-4o and GPT-4o-Mini's Vision Capabilities for Compositional Analysis from Dried Solution Drops.. doi.org. https://doi.org/10.1021/acsomega.5c01150