GPT-4o-mini
OPENAI Developer Architecture Profile
Intelligence (ELO)1300Chatbot Arena Verified
Max Context128,000Tokens
API Cost / 1M$0.75Blended Prompt + Completion
Model Capabilities
- Coding & Logic
- Fictional
- Drafting
- Classification
- Conversational
- Agentic
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
Granular Pricing Matrix
Input Tokens (Prompt)$0.15 / 1M
Output Tokens (Completion)$0.60 / 1M
Pricing data via OpenRouter. Sync: 3/16/2026
Evaluate Competitors
VS Engine MatchupGPT-4o-mini vs Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)VS Engine MatchupGPT-4o-mini vs Google: Gemini 3.1 Pro Preview Custom ToolsVS Engine MatchupGPT-4o-mini vs OpenAI: GPT-5.2-CodexVS Engine MatchupGPT-4o-mini vs Google: Gemini 3 Flash PreviewVS Engine MatchupGPT-4o-mini vs OpenAI: GPT-5.2 ProVS Engine MatchupGPT-4o-mini vs OpenAI: GPT-5.2