How much does GPT-4o cost?

GPT-4o costs $2.50 per million input tokens and $10 per million output tokens on standard pricing; other tiers (Standard, Batch, Fast (Priority)) are also available. A workload of 20M input and 5M output tokens a month is about $100.

What is the context length of GPT-4o?

GPT-4o accepts up to 128,000 tokens (128K) of input and can return up to 16,384 tokens in one response.

Does GPT-4o support tool calling and structured outputs?

Yes, GPT-4o supports function/tool calling and structured (JSON) outputs. Supported tools: Function calling, Structured outputs, JSON mode, Built-in web search, Log probabilities, Deterministic seed, Prompt caching.

What inputs and outputs does GPT-4o support?

GPT-4o accepts Text, Image, PDF as input and produces Text as output.

Which providers serve GPT-4o?

GPT-4o is available from 2 API providers: Azure, OpenAI. Prices can differ by provider.

When was GPT-4o released?

GPT-4o was released by OpenAI in 2024-05.

GPT-4o

gpt-4o

API Provider site

Multimodal GPT-4o "omni" model for text and image input. Built by OpenAI.

Prices updated recently

Input price

$2.50

per 1M tokens · Standard

Output price

$10

per 1M tokens · Standard

Input limit

128K

tokens

Output limit

16K

tokens

Input formats

TextImageVideoAudioPDF

Output formats

TextImageVideoAudioPDF

Compare

GPT-4o price history

12 price records since 4/1/2026 · 10 changes

GPT-4o cost calculator

Input20M tokens

Output5M tokens

$100/month

Standard pricing

Gemini 2.5 Pro$75
GPT-4.1$80

Overview

What is GPT-4o?

GPT-4o is a text & reasoning and vision model from OpenAI. Multimodal GPT-4o "omni" model for text and image input. Its 128K context window and $2.50 input price make it a candidate for quality-focused production applications.

Image understandingDocument analysisContent workflowsClassification

Benchmarks

GPT-4o benchmarks & speed

How GPT-4o scores on standardized evaluations, and where it lands among every model we track.

8.4

Intelligence Index

Better than 18% of 153 models

145tok/s

Output speed

Better than 75% of 119 models

864

DesignArena Elo

Better than 1% of 81 models

Reasoning

GPQA Diamond

54.3%

Graduate-level scientific reasoning · top 85%

HLE

2.4%

Humanity's Last Exam · top 99%

Latency & design

Time to first token: 0.84s
DesignArena win rate: 34.8%
Design battles judged: 1,780

Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.

Rates

GPT-4o pricing

Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.

Input · Standard

$2.50

Per 1M tokens

Cached input · Standard

$1.25

Per 1M tokens

Capabilities

GPT-4o Tools

Tools available when using GPT-4o through supported provider APIs.

Function calling

Supported

Structured outputs

Supported

JSON mode

Supported

Reasoning

Not supported

Built-in web search

Supported

Log probabilities

Supported

Deterministic seed

Supported

Parallel tool calls

Not supported

Prompt caching

Supported

Where to run it

GPT-4o API providers

2 providers serve GPT-4o. Prices are per 1M tokens; uptime is the last 24 hours.

Provider	Input	Output	Cached	Context	Uptime
Azure	$2.50	$10	—	128K	99.91%
OpenAI	$2.50	$10	$1.25	128K	99.77%

Azure

Input: $2.50
Output: $10
Cached: —
Context: 128K
Uptime: 99.91%

OpenAI

Input: $2.50
Output: $10
Cached: $1.25
Context: 128K
Uptime: 99.77%

Strengths and limitations

Strengths

Measured results (AA Intelligence 8.4 · DesignArena Elo 864 · Arena Elo 1178 · MMLU-Pro 69.9%) position it for demanding production work.
A 128K context window covers most focused application workflows.
Supports text & reasoning and vision workloads in one model.

Limitations

Generated tokens cost 4× more than input tokens, which matters for verbose responses.
The 128K context window is smaller than several long-context alternatives.
Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.

Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.

Same provider