OpenAI: GPT-4o-mini

File input Text input Image input Text output
Author's Description

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

Key Specifications
Cost
$$
Context
128K
Parameters
8B (Rumoured)
Released
Jul 17, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tool Choice Top P Logit Bias Temperature Logprobs Presence Penalty Stop Response Format Structured Outputs Tools Max Tokens Frequency Penalty Top Logprobs Seed
Features

This model supports the following features:

Response Format Tools Structured Outputs
Performance Summary

GPT-4o-mini, released by OpenAI on July 17, 2024, is a multimodal model supporting text and image inputs with text outputs. It consistently performs among the fastest models, ranking in the 80th percentile across seven benchmarks, and offers competitive pricing, typically providing cost-effective solutions in the 73rd percentile. Demonstrating exceptional reliability, it achieved a 100% success rate across all benchmarks. The model exhibits strong performance in several key areas. It achieved perfect accuracy in the Ethics (Baseline) benchmark, standing out as the most accurate model at its price point and among models of similar speed. Its General Knowledge (Baseline) score of 99.5% is also highly impressive, ranking it as the most accurate among models of comparable speed. In Coding (Baseline), it scored 87.0%, again being the most accurate among models this fast. While its Hallucinations Baseline accuracy was 76.0%, placing it in the 21st percentile, this indicates a potential area for improvement in acknowledging uncertainty. Its Instruction Following and Reasoning benchmarks, at 60.5% and 56.0% respectively, suggest moderate capabilities in these complex areas. Overall, GPT-4o-mini stands out for its remarkable balance of speed, cost-effectiveness, and high accuracy in critical knowledge and ethical domains.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.15
Completion $0.6
Input Cache Read $0.075

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/gpt-4o-mini 128K $0.15 / 1M tokens $0.6 / 1M tokens
Azure
Azure | openai/gpt-4o-mini 128K $0.15 / 1M tokens $0.6 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openai