o4-mini
A small, cost-efficient reasoning model that delivers much of o-series thinking at far lower price. The practical pick for high-volume tasks that still benefit from deliberate reasoning.
At a glance
Released
Apr 16, 2025
Provider
OpenAI
Context window
200,000 tokens
Max output
64,000 tokens
Modalities
Text + image → text
Knowledge cutoff
March 2024
API model ID
o4-miniLicense
Proprietary (API only)
Pricing
Standard
Input$1.10 / 1M
Output$4.40 / 1M
Batch (50% off)
Input$0.55 / 1M
Output$2.20 / 1M
A typical 1,500-token prompt with a 650-token answer costs ≈ $0.005 on the standard tier. Run your own prompt through the calculator →
What's new vs the previous model
Compared witho3-mini (January 2025)
- Better reasoning quality than o3-mini
- Added image input
- Strong price-to-reasoning ratio
- Less depth than full o3
Best use cases
Scalable reasoning
Runs deliberate problem-solving at high volume cheaply.
Coding tasks
Handles logic-heavy development with quick turnaround.
STEM support
Assists with math and science at modest cost.
Strengths & limitations
Strengths
- Cost-efficient reasoning
- Faster than o3
- Multimodal input
- Good value
Limitations
- Less depth than o3
- Older cutoff
How to test it
- No-code: open chatgpt.com and pick o4-mini from the model switcher — no API key needed.
- Playground: sign in to the OpenAI Platform and run prompts in the workbench, then copy the generated code.
- API: create a key in the OpenAI Platform and call the API (example below).
curl https://api.openai.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "o4-mini",
"messages": [{"role": "user", "content": "Explain tokenization in one paragraph."}]
}'