Skip to content
LLMs
OpenAI logo

OpenAI: GPT-4o

by OpenAI

OpenAI: GPT-4o is a large language model from OpenAI. It costs $2.50 per million input tokens and $10.00 per million output tokens. Its context window is 128K tokens.

Tool callingStructured outputPrompt cachingBatch tierimage inputfile input
Input / 1M tokens
$2.50
Output / 1M tokens
$10.00
Cached input / 1M
$1.25

On repeated prefixes

Context window
128K

tokens

Who serves it cheapest

2 hosts serve GPT-4o. Same weights, same API - the price difference is pure margin and routing.

Providers serving OpenAI: GPT-4o, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
AzureCheapest$2.50$10.00128K-99.9%
OpenAI$2.50$10.00128K-99.8%

The spread between Azure and OpenAI is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.

About GPT-4o

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...

Specifications

OpenAI: GPT-4o specifications
Model IDopenai/gpt-4o
ProviderOpenAI
Context window128K tokens
Max output16K tokens
Input modalitiestext, image, file
Output modalitiestext
Knowledge cutoff2023-10-31
Open weightsNo
ReleasedMay 13, 2024

Cheaper alternatives

Models that cost less than GPT-4o while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does OpenAI: GPT-4o cost?

$2.50 per million input tokens and $10.00 per million output tokens. Cached input reads cost $1.25 per million tokens.

What is the context window of OpenAI: GPT-4o?

128K tokens, with up to 16K tokens of output per request.

Which provider serves OpenAI: GPT-4o cheapest?

Azure at $2.50 per million input tokens - about the same cheaper than OpenAI, the most expensive of the 2 hosts serving it.

Confirm against the source: OpenAI official pricing.