o3-mini Official Specifications, Pricing & Benchmarks
o3-mini (o3-mini) by OpenAI, released 2024-12-20, featuring 200,000 context window, 100,000 max output tokens, and Text input.
📋 o3-mini Official API & System Card Specifications
Verified against official OpenAI developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- o3-mini
- Release Date
- 2024-12-20
- Weight License
- Proprietary (Undisclosed)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 200,000 tokens (200K)
- Max Output Tokens
- 100,000 tokens
- Input Modalities
- Text
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Cloud API only (Proprietary)
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 1.1
- Cached Input / 1M
- $ 0.55 -50%
- Output / 1M Tokens
- $ 4.4
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
💡 Custom temperature disabled in reasoning mode; adjust reasoning effort/budget instead.
📊 o3-mini Full Benchmark Scorecard
25 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 5 items
A coding benchmark that evaluates LLMs on 225 challenging Exercism programming exercises across C++, Go, Java, JavaScript, Python, and Rust. Models receive two attempts to solve each problem, with test error feedback provided after the first attempt if it fails.
A challenging multi-language coding benchmark that evaluates models' code editing abilities across C++, Go, Java, JavaScript, Python, and Rust.
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
A benchmark for evaluating large language models on real-world freelance software engineering tasks from Upwork. Contains over 1,400 tasks valued at $1 million USD total, ranging from $50 bug fixes to $32,000 feature implementations.
SWE-Lancer (IC-Diamond subset) is a benchmark of real-world freelance software engineering tasks from Upwork, ranging from $50 bug fixes to $32,000 feature implementations.
🤖 Agents & Tools 3 items
A benchmark for evaluating tool-agent-user interaction in retail environments. Tests language agents' ability to handle dynamic conversations with users while using domain-specific API tools and following policy guidelines.
Part of τ-bench (TAU-bench), a benchmark for Tool-Agent-User interaction in real-world domains. The airline domain evaluates language agents' ability to interact with users through dynamic conversations while following domain-specific rules and using API tools.
ComplexFuncBench is a benchmark designed to evaluate large language models' capabilities in handling complex function calling scenarios.
📐 Math 6 items
MATH dataset contains 12,500 challenging competition mathematics problems from AMC 10, AMC 12, AIME, and other mathematics competitions.
MGSM (Multilingual Grade School Math) is a benchmark of grade-school math problems. Contains 250 grade-school math problems manually translated from the GSM8K dataset into ten typologically diverse languages: Spanish, French, German, Russian, Chinese, Japanese, Thai, Swahili…
American Invitational Mathematics Examination 2024, consisting of 30 challenging mathematical reasoning problems from AIME I and AIME II competitions.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains.
LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses.
A benchmark of hundreds of original, exceptionally challenging mathematics problems crafted and vetted by expert mathematicians, covering most major branches of modern mathematics from number theory and real analysis to algebraic geometry and category theory.
📜 Long Context 1 items
🧠 Reasoning & Science 8 items
COLLIE is a grammar-based framework for systematic construction of constrained text generation tasks.
MMLU-ProX is a comprehensive multilingual benchmark covering 29 typologically diverse languages, building upon MMLU-Pro. Each language version consists of 11,829 identical questions enabling direct cross-linguistic comparisons.
Multi-IF benchmarks LLMs on multi-turn and multilingual instruction following. It expands upon IFEval by incorporating multi-turn sequences and translating English prompts into 7 other languages, resulting in 4,501 multilingual conversations with three turns each.
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A graph reasoning benchmark that evaluates language models' ability to find parent nodes in graphs with context length under 128k tokens, requiring understanding of graph structure and edge relationships.
A graph reasoning benchmark that evaluates language models' ability to perform breadth-first search (BFS) operations on graphs with context length under 128k tokens, returning nodes reachable at specified depths.
MultiChallenge is a realistic multi-turn conversation evaluation benchmark that challenges frontier LLMs across four key categories: instruction retention (maintaining instructions throughout conversations), inference memory (recalling and connecting details from previous…
SimpleQA is a factuality benchmark developed by OpenAI that measures the short-form factual accuracy of large language models. The benchmark contains 4,326 short, fact-seeking questions that are adversarially collected and designed to have single, indisputable answers.
📚 Knowledge & General 2 items
Instruction-Following Evaluation (IFEval) benchmark for large language models, focusing on verifiable instructions with 25 types of instructions and around 500 prompts containing one or more verifiable constraints.
Internal API instruction following (hard) benchmark - specific documentation not found in official sources.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to o3-mini
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is o3-mini open-source or proprietary?
o3-mini (o3-mini) is a proprietary commercial model by OpenAI. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of o3-mini?
o3-mini supports 200K input context and 100,000 max output tokens, priced at $1.1/1M input ($0.55/1M cached) and $4.4/1M output.