OpenAI
GPT-4o-mini
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective. GPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/). Check out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more. #multimodal
- Input / 1M tokens
- $0.150
- Output / 1M tokens
- $0.600
- Context window
- 128K tokens
- Provider
- OpenAI
- Cached input / 1M
- $0.075
- Knowledge cutoff
- 2023-10-31
Performance
Median streaming throughput and first-token latency measured by Artificial Analysis.
- Output tokens / sec
- 66 t/s
- Time to first token
- 0.57s
Benchmarks
Intelligence, coding, and math indexes plus the underlying evaluation scores.
- Intelligence Index
- 13
- Coding Index
- —
- Math Index
- 15
- MMLU-Pro
- 64.8%
- GPQA
- 42.6%
- HLE
- 4.0%
- LiveCodeBench
- 23.4%
- SciCode
- 22.9%
- MATH-500
- 78.9%
- AIME
- 11.7%
Benchmarks via Artificial Analysis