o1-mini — OpenAI | Modeldex

o1-mini

Deprecated

Smaller o1-series reasoning model, now superseded by o3-mini.

Updated 4 days agoStructured data from Modeldex catalog

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

Overview

o1-mini was OpenAI's cost-efficient reasoning model before o3-mini. It focuses on STEM reasoning without the broad world knowledge of the full o1.

History

o1-mini was released on 2024-09-12. This model is marked as deprecated and may be retired in the future.

Training & availability

OpenAI has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 128K tokens.
Max output: 65K tokens.
Input modalities: text.

Limitations

Text-only — cannot process images, audio, or video inputs.

Pricing

Input: $3.0000 per 1M tokens
Output: $12.0000 per 1M tokens

Use the cost calculator above to estimate monthly spend for your workload.

Quick start

Minimal example using the openai API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(api_key="sk-...")
resp = client.chat.completions.create(
    model="o1-mini",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $3/1M

Output tokens / month2.0M

@ $12/1M

Input cost

$15

5.0M × $3/1M

Output cost

$24

2.0M × $12/1M

Total / month

$39

$468 / year

Benchmarks

Benchmark	Score	Source
Aider PolyglotCoding	32.9% pass@2	Third-party Papers With Code

Integrations & tooling support

Tool calling: Not supported
Structured outputs: Not supported

Price vs quality

Poor value

Below-average benchmark performance for the price.

Quality percentile: 14.3%
Effective price: $9.75/1M
Pricing breakdown: $3/1M in
$12/1M out

Community ratings

No ratings yet. Be the first to rate o1-mini.