Skip to content
LLMs
OpenAI logo

OpenAI: GPT-4

by OpenAI

OpenAI: GPT-4 is a large language model from OpenAI. It costs $30.00 per million input tokens and $60.00 per million output tokens. Its context window is 8K tokens.

Tool callingStructured output
Input / 1M tokens
$30.00
Output / 1M tokens
$60.00
Cached input / 1M
-

Not supported

Context window
8K

tokens

Who serves it cheapest

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

Providers serving OpenAI: GPT-4, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
AzureCheapest$30.00$60.008K-100.0%
OpenAI$30.00$60.008K-100.0%

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

Benchmarks

Independent scores published alongside the catalogue.

Coding index
13.1

About GPT-4

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...

Specifications

OpenAI: GPT-4 specifications
Model IDopenai/gpt-4
ProviderOpenAI
Context window8K tokens
Max output4K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2021-09-30
Open weightsNo
ReleasedMay 28, 2023

Cheaper alternatives

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

Frequently asked

How much does OpenAI: GPT-4 cost?

$30.00 per million input tokens and $60.00 per million output tokens.

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

8K tokens, with up to 4K tokens of output per request.

Which provider serves OpenAI: GPT-4 cheapest?

Azure at $30.00 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.