openai

OpenAI: o3 Mini

The OpenAI o3 Mini is designed to handle text and file inputs with a context length of 200,000 tokens and supports both reasoning and tools integration. While it does not provide structured output or open weights, its capabilities in input handling and logical processing make it versatile for various tasks. This model stands as a solid choice for users who need robust reasoning and tool support but are willing to pay the price; with a blended benchmark score of 46.6 across two independent evaluations, it offers reliable performance. Given its pricing at $1.1 per million input tokens and $4.4 per million output tokens, it may be more suitable for projects requiring frequent interactions or larger datasets where cost is a consideration.

Quality Score
100/100
price + capability + benchmarks
Input Price
$1.10
per 1M tokens
Output Price
$4.40
per 1M tokens
Context Window
200,000
tokens

Benchmark results

Independent, published benchmarks. Blended score 46.6 across 2 benchmarks, last refreshed 2026-07-21. How scoring works →

BenchmarkMeasuresScore
Aider Polyglot code editing across languages 53.8
AI Index broad capability composite 31.3
Model ID
openai/o3-mini
Vendor
openai
Released
January 2025
Tokenizer
GPT
Input Modalities
text, file
Output Modalities
text
Max Output
100,000 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
yes

What it costs in practice

Computed from the current $1.10/M input and $4.40/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.04
Classify 1,000 customer emails 500k in / 50k out $0.77
A month of a busy support chatbot 5M in / 2M out $14.30

Similar models

Quick answers

How much does OpenAI: o3 Mini cost?
$1.10 per million input tokens and $4.40 per million output tokens.
What is OpenAI: o3 Mini's context window?
200,000 tokens, roughly 300 pages of text in a single request.
Does OpenAI: o3 Mini support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can OpenAI: o3 Mini process images?
No, it is text-only on the input side.