o4-mini
StandardCompact reasoning model optimized for fast, cost-efficient STEM performance.
Retains strong multimodal and agentic capabilities with tool use support. Balances speed and reasoning depth for everyday technical tasks.
▼
o4-mini is somewhat expensive at $1.10/M tokens input and $4.40/M tokens output. Cached input reads are priced at $0.28/M tokens, making repeated context cheaper. The model supports vision/image input, extended reasoning, a 200K context window.
Benchmarks
Specifications
Performance
Providers
Misc
Compare with
GPT 6 Astravs o4-miniGPT 5.6 Lunavs o4-mini
Claude Fable 5.1vs o4-miniClaude Opus 5vs o4-miniClaude Sonnet 5vs o4-miniClaude Haiku 4.5vs o4-mini
Gemini 3.8 Flashvs o4-miniGemini 3.5 Flashvs o4-miniGemini 3.5 Flash-Litevs o4-miniGemma 4 31Bvs o4-mini
Grok 4.6vs o4-miniGrok Build 0.1vs o4-miniGrok 4.1 Fastvs o4-mini
Muse Spark 1.3vs o4-mini
DeepSeek V4 Pro (0813)vs o4-miniDeepSeek V4 Flashvs o4-mini
MiniMax M3vs o4-mini
GLM 5.3vs o4-miniGLM 5.3 Flashvs o4-mini
Qwen3.8 Max (0902)vs o4-miniQwen3.7 Plusvs o4-miniQwen3 Coder Nextvs o4-mini
Nemotron 3 Ultravs o4-miniFrequently Asked Questions about o4-mini▼
When was o4-mini released?
▼
o4-mini was released on April 16, 2025.
Who created o4-mini?
▼
o4-mini was created by OpenAI.
How much does o4-mini cost?
▼
o4-mini costs $1.10/M input tokens and $4.40/M output tokens.
What is o4-mini API pricing?
▼
The o4-mini API is priced at $1.10 per million input tokens and $4.40 per million output tokens. You can access o4-mini through idapt.app alongside 200+ other AI models in one workspace.
Is o4-mini a reasoning model?
▼
Yes, o4-mini is a reasoning model. It can think step-by-step through complex problems before providing an answer, often yielding better results on difficult tasks like math, coding, and multi-step logic.
Does o4-mini support image or vision input?
▼
Yes, o4-mini supports vision/image input. You can share images in your conversation and the model will analyze and respond based on their content.
Does o4-mini support audio?
▼
No, o4-mini does not support audio input.
What is the context window of o4-mini?
▼
o4-mini has a context window of 200K tokens, meaning it can process approximately 150,000 words of context at once.
Is o4-mini open source?
▼
o4-mini is a proprietary model developed by OpenAI. The model weights and training data are not publicly available.
What is o4-mini good at?
▼
Based on benchmark data, o4-mini excels at: visual analysis and image understanding. It is OpenAI's capable model suitable for a wide range of tasks.
Where can I use o4-mini?
▼
You can chat with o4-mini on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access o4-mini through OpenAI's own API or platform.