GPT-5 Image Mini
image modelOpenAI
GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by GPT-5 Mini, with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...
Key facts
| Made by | OpenAI |
|---|---|
| Type | image model |
| Released | October 16, 2025 |
| Reads at once | 400,000 tokens |
| Price (API, per million tokens) | $2.5 in · $2 out |
| Input → output | file, image, text → image, text |
Questions about GPT-5 Image Mini
Who makes GPT-5 Image Mini?
GPT-5 Image Mini is made by OpenAI.
When was GPT-5 Image Mini released?
We first saw GPT-5 Image Mini listed on October 16, 2025.
How much does GPT-5 Image Mini cost?
Through OpenRouter it costs $2.5 per million input tokens and $2 per million output tokens. Prices change, so check the provider before you build on it.
How much text can GPT-5 Image Mini read at once?
Up to 400,000 tokens, roughly 300K words.
More from OpenAI
Whisper-SmallOpenAI · voice and audio model
Sep 26, 2022released
Whisper-Large-V3OpenAI · voice and audio model
Nov 7, 2023released
whisperOpenAI · voice and audio model
Sep 26, 2022released
Whisper-TinyOpenAI · voice and audio model
Sep 26, 2022released
Openai-Agents-Pythonopenai · developer tool
Mar 11, 2025released
Whisper-MediumOpenAI · voice and audio model
Sep 26, 2022released
Other ai image generation
Stable-Diffusion-XL-1.0Stability AI · image model
Jul 25, 2023released
Unslothunslothai · image model
Nov 29, 2023released
Stable-Diffusion-V1-5Stable Diffusion V1 5 · image model
Aug 30, 2024released
RealVisXL V5.0SG161222 · image model
Aug 5, 2024released
Dreamshaper-7Lykon · image model
Aug 26, 2023released
Z-Image-TurboTongyi MAI · image model
Nov 25, 2025released
Sd-TurboStability AI · image model
Nov 27, 2023released
SDXL-TurboStability AI · image model
Nov 27, 2023released
Modelcast collects this page automatically from public sources (OpenRouter). Facts are copied from those sources, not written by the maker. Not affiliated with OpenAI.