---
id: "openai/gpt-4o-mini"
also: ["openai/gpt-4o-mini", "requesty/openai/gpt-4o-mini", "vercel/openai/gpt-4o-mini"]
card_usd_per_m: "0.15 in, 0.6 out, at openai"
cheapest_list_usd_per_m: "0.15 in, 0.6 out, at azure on openrouter"
cheapest_effective_usd_per_m: "0.1105 in, 0.5976 out, at azure on openrouter"
context: 128000
max_output: 16384
input: ["text", "image", "file"]
output: ["text"]
released: "2024-07-18"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "prediction", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p", "web_search_options"]
endpoints: 10
gateways: "requesty (5), openrouter (3), vercel (2)"
no_training: 10
trains: 0
retains_prompts: 2
coding: 11.4000
---
# 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