GPT o4 Mini
GPTCompact
ThinkingTool UseVisionStructured Output
About this model
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...
Performance Tier
Compact
GPT o4 Mini is a compact model from GPT : optimized for speed and affordability.
Small, fast, and affordable. Optimized for speed and low cost, great for high-volume or simple tasks.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $1.10 |
| Output (completion) | $4.40 |
| Cache read | $0.275 |
Capabilities
Context Length200K
Max Output Tokens100K
TokenizerGPT
Inputimage, text, file
Outputtext
Release DateApril 16, 2025
Benchmarks
General Intelligence
MMLU
85.2%
GPQA Diamond
78.4%
Mathematics
MATH-500
97.3%
AIME 2025
92.7%
Programming
HumanEval
90%
SWE-bench Verified
68.1%
Reasoning
Humanity's Last Exam
14.7%
Recommended Use Cases
MathematicsCodingAnalysisResearch
Strengths
- Outstanding mathematical reasoning (MATH-500 97.3%)
- Chain-of-thought reasoning at an affordable price
- Strong competition math performance (AIME 93.4%)
- Good software engineering capabilities for a reasoning model
Limitations
- Slower than standard GPT models due to reasoning overhead
- Less suited for creative or conversational tasks
Resources
This model may use your data for training
