Model details
o4-mini was introduced as a compact reasoning model designed to be faster and more affordable than its larger o3 sibling while still supporting tool-based workflows such as Python execution and web browsing. It is multimodal by default, accepting image inputs alongside text, which broadens its usefulness for tasks that mix visual context with code, math, or analytical reasoning. The model is positioned for developers and teams that want responsive reasoning behavior without the higher cost of top-tier reasoning systems, making it well suited to coding assistance, step-by-step problem solving, and lightweight agent-style workflows that benefit from image understanding and tool integration. Independent evaluation work from METR, which received pre-release checkpoints roughly three weeks ahead of launch, provides a useful signal about real-world capability. METR's preliminary tests on the HCAST general autonomy suite and the RE-Bench AI R&D suite found that o4-mini's 50% time horizon exceeded earlier measurements and sat between roughly 1.5x and 1.8x that of comparable predecessors, suggesting meaningful gains in handling longer, multi-step tasks. Combined with its multimodal inputs and tool-use support, those results point to a model that is best matched to workloads where moderate reasoning depth, image-grounded understanding, and cost-effective throughput matter more than the absolute strongest reasoning performance in the lineup.
From a practical standpoint, o4-mini's appeal lies in balancing reasoning quality with deployment efficiency. Its support for tool calling and image inputs makes it a flexible choice for automated pipelines that need to interpret screenshots, diagrams, or document pages while orchestrating external tools to retrieve or compute information. The model's compact footprint within the broader o-series positions it as a sensible default for production assistants, data analysis helpers, and developer-facing tools that require dependable reasoning without the latency or expense of the largest reasoning models. Teams exploring agentic prototypes can also draw on independent benchmark context to calibrate expectations around autonomy and step-by-step task completion when integrating o4-mini into their workflows.
Transparent token rates
Rates are shown per one million tokens. Combined means one million input plus one million output tokens.
OpenRouter
On February 13, 2026, alongside the previously announced retirement of GPT‑5 (Instant, Thinking, and Pro), we will retire GPT‑4o, GPT‑4.1, GPT‑4.1 mini, and OpenAI o4-mini from ChatGPT. In the API, there are no changes at this time.
DevPass (LLM Gateway)
Independent benchmark aggregator llm-stats.com (page date September 22, 2026) ranks OpenAI's o4-mini at #146 on its composite LLM Stats Score, with category standings including Chat (58 of 133), Healthcare (70 of 245), Vision (91 of 210), Math (97 of 327), Reasoning (138 of 366), Writing (62 of 114), Search (65 of 90), The page enumerates specific benchmark scores for o4-mini sourced to openai.com, including AIME 2024 (rank 2, score 0.93/1, accuracy without tools), AIME 2025 (rank 36, score 0.93/1, accuracy without tools), MathVista (rank 5, score 0.84/1), and MMMU. These figures provide a quantitative snapshot of o4-mini's mathemati
OpenRouter
Wikiwand's encyclopedia entry for OpenAI o4-mini corroborates the model's timeline: initial release on April 16, 2025, broader rollout including free-tier ChatGPT users on April 24, 2025, retirement announced January 29, 2026, and effective ChatGPT retirement on February 13, 2026. It identifies the predecessor as o3-mi The entry confirms o4-mini was a vision-language model capable of processing text and images, including analyzing whiteboard sketches during its chain-of-thought phase. Both o4-mini and o4-mini-high were released as vision-language models, distinguishing o4-mini from earlier text-only o-series entries. The page is a th
Model Oracle AI
A Hacker News comment dated April 16, 2025 from an OpenAI employee (tedsanders) clarifies that in ChatGPT, o4-mini is replacing o3-mini as a straight 1-to-1 upgrade, while in the API o4-mini is introduced as a new model option with o3-mini continuing to be supported so developers who built products atop o3-mini can mai The same thread explains the rationale behind keeping both models available: launching a new model would otherwise risk breaking production apps, and developers are given the option to test both and switch when they like. The commenter also notes that naming and offering improvements were being considered later in 2025
OpenRouter
Browse benchmarks, providers, pricing, deployment options, and compatibility details for o4 Mini on AI Stats.
This exact model name is also listed by 17 other providers.
