OpenAI o4-mini
OpenAI
OpenAI's o4-mini (April 2025), a fast, cost-efficient reasoning model that halves the price of o3-mini while matching it on most reasoning benchmarks. It supports much higher usage limits than o3 - a strong high-throughput reasoning option - and can reason with images.
Strengths
- Most cost-effective reasoning model in OpenAI's lineup
- Strong AIME math performance and competitive SWE-bench Verified coding for its size
- Halves o3-mini's price with comparable performance
- Supports much higher usage limits than o3 (high-throughput)
- Reasons with images
Caveats
- 'mini' capacity trails o3 and GPT-5.x on the hardest tasks
- 200K context is smaller than GPT-5.x
- Reasoning latency higher than non-reasoning minis
- Vendor
- OpenAI
- Context Window
- 200,000 tokens
- Max Output
- 100,000 tokens
- License
- Proprietary
- Release Date
- 2025-04-16
- Modalities
- textimage
Capabilities
Vision
Audio
Video
Tool Use
Resources
Pricing
$0.55 per 1M input tokens, $2.20 per 1M output tokens - about half o3-mini's price with comparable reasoning performance.