OpenAI Inc.
o4-mini-2025-04-16:medium
o3-mini is OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini also supports key developer features, like Structured Outputs, function calling, Batch API, and more. Like other models in the o-series, it is designed to excel at science, math, and coding tasks.
Advanced Reasoning
Caching Support
Pricing
$1.10
Input tokens per million
$4.40
Output tokens per million
Caching Pricing
$1.10
Cache write per million
$0.28
Cache read per million
Technical Specifications
Context Window
200K tokens
Max Output Tokens
100K tokens
Global Availability
Last Updated
N/A