The OpenAI o3-mini is a high-speed, cost-effective reasoning model designed for STEM applications, with strong performance in science, mathematics, and coding. Launched in January 2025, it includes essential developer features such as function calling, structured outputs, and developer messages. The model offers three reasoning effort levels—low, medium, and high—allowing users to optimize between deeper analysis and faster response times. Unlike the o3 model, it lacks vision capabilities. Initially available to select developers in API usage tiers 3-5, it can be accessed via the Chat Completions API, Assistants API, and Batch API.
GPT-4.1 Nano, launched by OpenAI on April 14, 2025, is the company's fastest and most affordable model to date. Designed for low-latency tasks such as classification, autocomplete, and fast inference scenarios, it combines compact architecture with robust capabilities. Despite its size, it supports an impressive 1 million token context window and delivers strong benchmark results, achieving 80.1% on MMLU and 50.3% on GPQA. With a knowledge cutoff of June 2024, GPT-4.1 Nano offers exceptional value at just $0.10 per million input tokens and $0.40 per million output tokens, with a 75% discount applied to cached inputs, making it ideal for high-volume, cost-sensitive deployments.
| o3-mini | GPT-4.1 Nano | |
|---|---|---|
Web Site
| ||
Provider
| ||
Chat
| ||
Release Date
| ||
Modalities
| text | text images |
API Providers
| OpenAI API | OpenAI API |
Knowledge Cut-off Date
| Unknown | - |
Open Source
| No | No |
Pricing Input
| $1.10 per million tokens | $0.10 per million tokens |
Pricing Output
| $4.40 per million tokens | $0.40 per million tokens |
MMLU
| 86.9% pass@1, high effort Source | 80.1% Source |
MMLU-Pro
| Not available | - |
MMMU
| Not available | 55.4% Source |
HellaSwag
| Not available | - |
HumanEval
| Not available | - |
MATH
| 97.9% pass@1, high effort Source | - |
GPQA
| 79.7% 0-shot, high effort Source | 50.3% Diamond Source |
IFEval
| Not available | 74.5% Source |
SimpleQA
| - | - |
AIME 2024 | - | 29.4% Source |
AIME 2025 | - | - |
Aider Polyglot
| - | - |
LiveCodeBench v5
| - | - |
Global MMLU (Lite)
| - | 66.9% Source |
MathVista
| - | 56.2% Image Reasoning Source |
Mobile Application |
Compare AI. Test. Benchmarks. Mobile Apps Chatbots, Sketch
Copyright © 2025 All Right Reserved.