Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
Cloudflare AI Gateway logo

Model details

GPT-4o

GPT-4o is OpenAI's flagship omni-modal model, with the "o" standing for "omni" to reflect its unified handling of text, audio, image, and video within a single system rather than routing through separate models for each modality. Positioned as the successor to GPT-4 Turbo, it was introduced on May 13, 2024 and is designed to make human-computer interaction feel more natural by responding to audio inputs in as little as 232 milliseconds, averaging 320 milliseconds—comparable to human conversational timing. By collapsing what was previously a pipeline of Whisper transcription, GPT-4 Turbo reasoning, and a text-to-speech layer into one model, GPT-4o aims to simplify multimodal workflows and unlock new kinds of voice and vision experiences.

In practical terms, GPT-4o is targeted at developers and product teams who want a single model for mixed-media applications such as real-time voice assistants, interview preparation, image-grounded Q&A, and code or text tasks that may be interspersed with visual references. OpenAI describes it as matching GPT-4 Turbo on English text and code while delivering significant gains on non-English languages, and as especially stronger on vision and audio understanding compared with prior models. It is also positioned as faster and roughly 50% cheaper in the API than GPT-4 Turbo, making it a natural fit for high-volume conversational and multimodal deployments where latency, language coverage, and cost together shape the user experience.

Cloudflare AI Gatewayopenai/gpt-4ogpt

Quick Info

Powered by
Provider
Cloudflare AI Gateway
Model key
openai/gpt-4o
Release date
May 13, 2024
Last updated
Aug 6, 2024
Knowledge cutoff
2023-09
AI SDK package
@ai-sdk/openai
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$1.25
Output token cost
$5.00

Limits

Output tokens
16,384 tokens
Context window
128,000 tokens

Transparent token rates

Compare GPT-4o pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about GPT-4o

Cloudflare AI Gateway

Coverage

On February 13, 2026, alongside the previously announced retirement⁠ of GPT‑5 (Instant, Thinking, and Pro), we will retire GPT‑4o, GPT‑4.1, GPT‑4.1 mini, and OpenAI o4-mini from ChatGPT. In the API, there are no changes at this time.

Videos about GPT-4o

More models around GPT-4o