OpenAI: GPT-5 Image Mini

openai/gpt-5-image-mini · OpenAIUnmeasurable

Declared family: GPT
Declared tokenizer tag: GPT
Entered catalogue: 16 October 2025
Measurement: Deferred: measurement cost above the per-model cap
Evidence confidence: Unknown

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Not measured yet	we measured it
How its API is set up	Set up identically to 1 other listing, field for field	api_803e17c9
How much it can read and write	Reads up to 400,000 tokens at once, writes up to 128,000	its own listing
Whether it thinks before answering	Always reasons, and cannot be turned off	its own listing

Declared record

What the catalogue claims about this model

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...

Modalities: text+image+file->text+image
Declared tokenizer: GPT
Prompt price: $2.50 / M tokens
Completion price: $2.00 / M tokens

Supported parameters

include_reasoninglogprobsmax_tokensreasoningresponse_formatseedstructured_outputstemperaturetop_logprobstop_pverbosity

defaults: {"temperature":null,"top_p":null,"frequency_penalty":null}

Catalogue entry

History

Every observation, kept as taken

16 October 2025Enters the OpenRouter catalogue declared as GPT.