GPT-4o mini — OpenAI | Modeldex

GPT-4o mini

Active77.1Strong

Low-cost, fast multimodal model for high-volume tasks.

Updated 4 days agoStructured data from Modeldex catalog

VisionMathAgenticBudget

Knowledge cutoff

Oct 31, 2023(2.5 years ago)

API release

Jul 18, 2024(1.8 years ago)

Intelligence Index

77.1/ 100

Strongweighted across 4 benchmarks

Math: 81.7
General knowledge: 72.5

Computed as the mean of per-category averages across MMLU, GPQA, SWE-bench, HumanEval, MATH, GSM8K, AIME, Aider Polyglot and more. See each benchmark for methodology.

Overview

GPT-4o mini is OpenAI's small, affordable model designed for high-throughput, latency-sensitive applications. It supports text and image inputs with tool calling and structured outputs.

History

GPT-4o mini became available via the OpenAI API on 2024-07-18.

Training & availability

Training data has a knowledge cutoff of 2023-10-31 — information about events after that date is unlikely to appear in the model's responses. OpenAI has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 128K tokens.
Max output: 16K tokens.
Input modalities: text, image.
Intelligence Index: 77.1/100.

Strongest categories: Math (82), General knowledge (73).

Recommended for: vision, math, agentic, cheap.

Limitations

The knowledge cutoff is 30 months old — this model will not know about recent events, releases, or API changes.

Pricing

Input: $0.1500 per 1M tokens
Output: $0.6000 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="gpt-4o-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

@ $0.15/1M

Output tokens / month2.0M

@ $0.6/1M

Input cost

$0.75

5.0M × $0.15/1M

Output cost

$1.2

2.0M × $0.6/1M

Total / month

$1.95

$23.4 / year

Providers & performance

2 providers

Multi-provider inference routes for this model — sorted by throughput. Latency is time-to-first-token; throughput is output tokens per second. Data from OpenRouter, measured over the last 30 minutes.

Provider	Throughput	Latency (TTFT)	Input $ / 1M	Output $ / 1M	Context	Quant	Supports
Azure	42tok/s	624ms	$0.15	$0.6	128K	—	json
OpenAI	29tok/s	526ms	$0.15	$0.6	128K	—	tools · json

Benchmarks

Benchmark	Score	Source
GSM8KMath	93.2% accuracy	Self-reported OpenAI system card
MATHMath	70.2% accuracy	Self-reported OpenAI system card
MMLUGeneral knowledge	82% accuracy	Self-reported OpenAI system card

Integrations & tooling support

Tool calling: Supported
Structured outputs: Supported

Price vs quality

Budget option

Cheap and cheerful — useful for high-volume tasks.

Quality percentile: 7.7%
Effective price: $0.487/1M
Pricing breakdown: $0.15/1M in
$0.6/1M out

Community ratings

No ratings yet. Be the first to rate GPT-4o mini.