~openai

OpenAI: GPT Mini Latest

The OpenAI GPT Mini Latest is a language model that supports three input modalities: file, image, and text. It has a high context length of 400,000 tokens and can generate output with up to 128,000 completion tokens. Additionally, it provides tools for users, supports reasoning capabilities, and does not produce structured output. This model is suitable for those requiring flexible input options and extensive context handling. With a pricing structure of $0.75 per million input tokens and $4.5 per million output tokens, users should consider the OpenAI GPT Mini Latest if they prioritize these features without being constrained by its current lack of independent benchmark coverage, which indicates no proven performance standing at this time.

Quality Score
100/100
price + capability + benchmarks
Input Price
$0.75
per 1M tokens · checked 2026-09-23
Output Price
$4.50
per 1M tokens · checked 2026-09-23
Context Window
400,000
tokens
Model ID
~openai/gpt-mini-latest
Vendor
~openai
Released
April 2026
Tokenizer
Router
Input Modalities
file, image, text
Output Modalities
text
Max Output
128,000 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.75/M input and $4.50/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.03
Classify 1,000 customer emails 500k in / 50k out $0.60
A month of a busy support chatbot 5M in / 2M out $12.75

Similar models

Quick answers

How much does OpenAI: GPT Mini Latest cost?
$0.75 per million input tokens and $4.50 per million output tokens.
What is OpenAI: GPT Mini Latest's context window?
400,000 tokens, roughly 600 pages of text in a single request.
Does OpenAI: GPT Mini Latest support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can OpenAI: GPT Mini Latest process images?
Yes, it accepts image input.

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.