OpenAI: GPT-4o

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

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities. For benchmarking against other models, it was briefly called ["im-also-a-good-gpt2-chatbot"](https://twitter.com/LiamFedus/status/1790064963966370209) #multimodal

Key Specifications
Cost
$$$$$
Context
128K
Parameters
200B (Rumoured)
Released
May 12, 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

OpenAI's GPT-4o, released on May 12, 2024, demonstrates a strong overall performance profile, particularly excelling in speed and reliability. It consistently performs among the fastest models, ranking in the top tier (75th percentile) across benchmarks. While its pricing is moderate (20th percentile), it offers exceptional reliability with a 100% success rate, indicating minimal technical failures. GPT-4o exhibits perfect accuracy in both the Hallucinations Baseline and Ethics (Baseline) benchmarks, showcasing its ability to acknowledge uncertainty and adhere to ethical principles. It also performs very well in General Knowledge (99.5% accuracy) and Email Classification (99.0% accuracy). Its instruction-following capabilities are robust (69.0% accuracy, 80th percentile), and it demonstrates strong reasoning (84.0% accuracy, 76th percentile) and coding proficiency (93.0% accuracy, 88th percentile). Notably, for Hallucinations and Ethics, it is the most accurate model at its price point and among models of similar speed. Its multimodal capabilities, supporting both text and image inputs, further enhance its versatility.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $2.5
Completion $10
Input Cache Read $1.25

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
OpenAI
OpenAI | openai/gpt-4o 128K $2.5 / 1M tokens $10 / 1M tokens
Azure
Azure | openai/gpt-4o 128K $2.5 / 1M tokens $10 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by openai