Create with OpenAI GPT-4o
GPT-4o offers significantly faster performance and is 50% more cost-effective than GPT-4 Turbo in the API
Model capabilities
GPT-4o is a unified model trained end-to-end on text, vision, and audio, marking OpenAI's initial foray into exploring multimodal AI capabilities and limitations.
Speak with ChatGPT
Chat about images
Real-time translation
GPT-4o capabilities
ChatGPT has voice and image capabilities, enhancing interaction through voice conversations and visual inputs. Users can now discuss photos, get travel insights, solve math problems, and plan meals visually in real time.
How to Get an OpenAI API Key with AI/ML API
Sign Up
Begin by signing up on our AI/ML API platform. Create your account to gain access to a wide range of powerful AI models and tools.
Create API Key
In the Playground, navigate to the Key Management section and click on Create API Key. You can easily activate or deactivate your keys as needed.
Integrate AI
After creating your API key, you can integrate AI models into your application by following the guidelines provided in our API reference.
Model Scoring
GPT-4o matches the text, reasoning, and coding intelligence of GPT-4 Turbo, while establishing new benchmarks in multilingual, audio, and vision capabilities.
Enhanced Reasoning
GPT-4o achieves a record score of 88.7% on the 0-shot COT MMLU for general knowledge questions, utilizing our new Simple Evals library. Additionally, it sets a top score of 87.2% on the traditional 5-shot no-CoT MMLU.
Get API Key%20vs.%20Model%20(2).webp)
Audio ASR Performance
GPT-4o significantly enhances speech recognition capabilities beyond Whisper-v3, offering marked improvements across all languages, especially in those with fewer resources.
Get API KeyAudio Translation Performance
GPT-4o establishes a new benchmark in speech translation, surpassing Whisper-v3 and popular models from Google and Meta on MLS benchmarks.
Vision Understanding Evals
GPT-4o reaches state-of-the-art levels in visual perception benchmarks. All vision assessments are conducted 0-shot, including MMMU, MathVista, and ChartQA, which utilize 0-shot CoT methodologies.
Get API Key