Skip to model information

GPT-5 Mini

Deprecated

An OpenAI model with a 400K-token context window, image input and tool calling. On the OpenAI API since August 7, 2025, now deprecated.

Access details: OpenAI API

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

gpt-5-mini
Updated Sep 23, 2026

Capabilities & limits

Context window
400K
Maximum output
128K
Image input
Supported
Tool calling
Supported
Structured output
Supported

Pricing

USD / 1M tokens
Input
$0.25
Output
$2.00

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

$0.25 per 1M tokens

Standard output

$2.00 per 1M tokens

Cached input

$0.025 per 1M tokens

Other tiers per 1M tokens (short context): Batch: $0.125 input / $1 output / $0.0125 cached; Flex: $0.125 input / $1 output / $0.0125 cached; Fast mode: $0.45 input / $3.6 output / $0.045 cached.

Price history
Sep 23, 2026

Input $0.25 per million tokens

Sep 23, 2026

Output $2.00 per million tokens

Technical details

Parameters
Not published
Active parameters
Not published
Architecture
Not published
Training / knowledge cutoff
May 31, 2024
Input modalities
Text, image
Output modalities
Text

Release & lifecycle

First available
Aug 7, 2025
deprecated
Jun 11, 2026

Considering a switch?

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

Compare with DeepSeek V4 Flash Vision Exp →

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