← Back to all models

GPT-4o mini

gpt-4o-mini

GPT-4o mini from OpenAI is their most advanced and cost-efficient small model. It is multi-modal (accepting text or image inputs and outputting text) and has higher intelligence than gpt-3.5-turbo but is just as fast.

Available at 12 Providers

Provider Source Input Price ($/1M) Output Price ($/1M) Description Free
vercel vercel Input: $0.15 Output: $0.60 GPT-4o mini from OpenAI is their most advanced and cost-efficient small model. It is multi-modal (accepting text or image inputs and outputting text) and has higher intelligence than gpt-3.5-turbo but is just as fast.
poe poe Input: $0.14 Output: $0.54 This intelligent small model from OpenAI is significantly smarter, cheaper, and just as fast as GPT-3.5 Turbo. Check out the newest version of this bot here: https://poe.com/GPT-5-mini.
abacus models-dev Input: $0.15 Output: $0.60 Provider: Abacus, Context: 128000, Output Limit: 16384
githubmodels models-dev Input: $0.00 Output: $0.00 Provider: GitHub Models, Context: 128000, Output Limit: 16384
azure models-dev Input: $0.15 Output: $0.60 Provider: Azure, Context: 128000, Output Limit: 16384
helicone models-dev Input: $0.15 Output: $0.60 Provider: Helicone, Context: 128000, Output Limit: 16384
cloudflareaigateway models-dev Input: $0.15 Output: $0.60 Provider: Cloudflare AI Gateway, Context: 128000, Output Limit: 16384
openai models-dev Input: $0.15 Output: $0.60 Provider: OpenAI, Context: 128000, Output Limit: 16384
requesty models-dev Input: $0.15 Output: $0.60 Provider: Requesty, Context: 128000, Output Limit: 16384
azurecognitiveservices models-dev Input: $0.15 Output: $0.60 Provider: Azure Cognitive Services, Context: 128000, Output Limit: 16384
githubcopilot litellm Input: $0.00 Output: $0.00 Source: github_copilot, Context: 64000
openrouter openrouter Input: $0.15 Output: $0.60 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 Context: 128000