← Models

o4-mini

OpenAI · o-series

Cost-effective reasoning model retained as a legacy reference after retirement from ChatGPT defaults.

Type
language
Context
200K tokens
Max Output
100K tokens
Status
legacy
Input
$1.1/1M tok
Output
$4.4/1M tok
API Access
Yes
License
proprietary
reasoning cost-efficient planning analysis production
Released April 2025 · Updated March 6, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on February 15, 2026.

o4-mini is a reasoning-capable model tier designed to balance analytical strength with production-friendly cost. OpenAI retired o4-mini from ChatGPT on February 13, 2026 while leaving API access unchanged, so it now reads better as a legacy route than a current public default.

Capabilities

The model handles structured decision tasks, planning, and medium-complexity technical analysis well. It is practical for systems that need reliable reasoning at scale.

Technical Details

o4-mini sits between throughput-focused low-cost tiers and premium reasoning tiers. It is a good candidate for routing architectures that reserve expensive models for only the hardest requests.

Pricing & Access

Available via OpenAI API model catalog where supported. Since pricing and availability can change, teams should verify current values from official OpenAI pricing documentation.

Best Use Cases

Good fit for compatibility-sensitive reasoning workflows that still rely on the older o-series behavior. For new public-facing OpenAI defaults, the GPT-5 family is now the more current recommendation.

Comparisons

Compared with o3, o4-mini usually trades some reasoning depth for lower operating cost. Compared with GPT-5 mini and GPT-5.3, o4-mini is now the older reasoning-leaning route in OpenAI’s public lineup. Compared with Gemini 2.5 Flash, choice usually depends on workload profile and ecosystem integration.