GPT-4o mini
ActiveLow-cost, fast multimodal model for high-volume tasks.
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.
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 |
| MMLU-ProGeneral knowledge | 63.1% 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
- $0.4875/1M
- Pricing breakdown
- $0.15/1M in
$0.6/1M out
vs 4 benchmarks
/ 1M tokens (input + 3× output)
Community ratings
No ratings yet. Be the first to rate GPT-4o mini.
Rate GPT-4o mini
Sign in to rate and review.
Comments
Sign in to leave a comment.