OpenAI: o4 Mini

Image input File input Text input Text output
Author's Description

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 and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains. Despite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.

Key Specifications
Cost
$$$$$
Context
200K
Released
Apr 16, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Reasoning Structured Outputs Response Format Seed Max Tokens Tool Choice Tools Include Reasoning
Features

This model supports the following features:

Response Format Tools Reasoning Structured Outputs
Performance Summary

OpenAI o4-mini demonstrates a balanced performance profile, excelling in reliability while offering moderate speed and premium pricing. Its exceptional reliability, with a 100% success rate across all benchmarks, ensures consistent and usable responses. The model's speed performance is moderate, ranking in the 38th percentile, indicating it performs adequately but not among the fastest models. Pricing is positioned at a premium level, falling into the 18th percentile, suggesting it is a more expensive option compared to many alternatives. In terms of specific benchmarks, o4-mini shows outstanding accuracy in General Knowledge (100%), achieving perfect scores and being the most accurate model at its price point and speed. It also exhibits strong performance in Reasoning (98% accuracy, 93rd percentile) and Coding (94% accuracy, 92nd percentile), aligning with its description as a compact reasoning model with competitive coding capabilities. Mathematics (93% accuracy, 77th percentile) and Ethics (99% accuracy, 52nd percentile) also show high accuracy. A notable area for improvement is Hallucinations, where its 86% accuracy (28th percentile) suggests it occasionally fails to acknowledge uncertainty. Instruction Following, while showing 76% accuracy, ranks in the 88th percentile, indicating strong relative performance despite the lower absolute score. Its cost-efficiency is particularly evident in Reasoning and Instruction Following, where it ranks in the 11th and 12th percentile for cost, respectively.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1.1
Completion $4.4
Input Cache Read $0.275
Web Search $10000

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/o4-mini-2025-04-16 200K $1.1 / 1M tokens $4.4 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openai