Skip to model information

o3-mini

Deprecated

An OpenAI model with a 200K-token context window and tool calling. On the OpenAI API since January 31, 2025, now deprecated.

Access details: OpenAI API

An alias. The provider can point it at a newer version.

o3-mini
Updated Sep 23, 2026

Capabilities & limits

Context window
200K
Maximum output
100K
Image input
Unsupported
Tool calling
Supported
Structured output
Supported

Pricing

USD / 1M tokens
Input
$1.10
Output
$4.40

Standard rates per million tokens. Discounts and long-context rates, where offered, are on OpenAI's pricing page.

Full rate card 3 rates

All prices in USD.

Standard input

$1.10 per 1M tokens
  • standard processing

Cached input

$0.55 per 1M tokens
  • prompt caching

Standard output

$4.40 per 1M tokens
  • standard processing

Batch API: $0.55 input / $2.20 output per 1M tokens. Deprecated: shutdown scheduled October 23, 2026 (deprecations page).

Price history
Sep 23, 2026

Input $1.10 per million tokens

Sep 23, 2026

Output $4.40 per million tokens

Technical details

Parameters
Not published
Active parameters
Not published
Architecture
Not published
Training / knowledge cutoff
Oct 01, 2023
Input modalities
Text
Output modalities
Text

Release & lifecycle

First available
Jan 31, 2025
deprecated
As of Sep 13, 2026

Considering a switch?

Specs only go so far. Try both on your own tasks and compare quality, speed and cost.

Compare with Grok Build 0.1 →

Prices and availability as of October 20, 2026. OpenAI's own pages have the latest.