WWhichAITry via Vercel AI Gateway
Models/OpenAI
OpenAI · released 2025-08

GPT-5 Mini

GPT-5 shrunk for scale.

context
200K
output max
32K
input /M
$0.40
output /M
$1.60
cached in /M
$0.04
modalities
T·I
Verdict

What it's actually good at

Strengths

  • +Cheap per token
  • +Fast first-token
  • +Good tool calling

Weaknesses

  • Weaker on nuanced writing than flagship

Our scores

reasoning
8.0
coding
8.0
writing
7.0
speed
9.0
value
10.0
Lightweight sibling of GPT-5. Low latency, low cost, retains most of the flagship's reasoning.
Pricing

Cost at common volumes

Monthly volumeInputOutputEst. monthly
Side project1M tok0.3M tok$0.88
Growing app50M tok15M tok$44.00
Production500M tok150M tok$440.00
Scale5000M tok1500M tok$4400.00

Estimates assume uncached input. Prompt caching and batch APIs can cut this by 50–90% for many workloads. Use the calculator →

Head-to-head

Compare GPT-5 Mini