Skip to content
LLMs
OpenAI logo

OpenAI: GPT-4o (2024-08-06)

by OpenAI

OpenAI: GPT-4o (2024-08-06) 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 cachingimage 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 (2024-08-06). Same weights, same API - the price difference is pure margin and routing.

Providers serving OpenAI: GPT-4o (2024-08-06), cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
AzureCheapest$2.50$10.00128K-100.0%
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 (2024-08-06)

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o ("o" for "omni") is...

Specifications

OpenAI: GPT-4o (2024-08-06) specifications
Model IDopenai/gpt-4o-2024-08-06
ProviderOpenAI
Context window128K tokens
Max output16K tokens
Input modalitiestext, image, file
Output modalitiestext
Knowledge cutoff2023-10-31
Open weightsNo
ReleasedAugust 6, 2024

Cheaper alternatives

Models that cost less than GPT-4o (2024-08-06) while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does OpenAI: GPT-4o (2024-08-06) 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 (2024-08-06)?

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

Which provider serves OpenAI: GPT-4o (2024-08-06) 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.