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
Pricing per 1M Tokens
| Input (Prompt) | $0.15 |
| Output (Completion) | $0.60 |
| Cache Read | $0.07 |
| Cache Write | Free |
| Image | N/A |
Specifications
| Context Length | 128K |
| Max Output Tokens | 16K |
| Input Modalities | Text + Image + File |
| Output Modalities | Text |
| Tokenizer | GPT |
| Instruct Type | N/A |
| Top Provider Context | 128K |
| Top Provider Max Output | 16K |
| Moderated | Yes |
Compare this model
See how OpenAI: GPT-4o-mini stacks up against other models.
More from OpenAI
Last updated: March 23, 2026
First tracked: March 23, 2026