OpenAI

OGPT-5API

GPT-5 (OpenAI): live API pricing, context window and the best open-source alternatives, tracked daily by OpenSourceAI.tech.

Context window
400K
tokens
Input price
$1.25
per M tokens
Output price
$10
per M tokens
Provider
OpenAI

Prices update automatically — checked hourly against provider list prices.

See open-source alternatives → Compare all model prices

Benchmarks & performance

Independent benchmark scores for GPT-5, measured by Artificial Analysis. Higher is better.

Intelligence index34.7
Coding index37.8
Math index94.3
GPQA85.4%
MMLU-Pro87.1%
Humanity's Last Exam26.5%
Long Context Reasoning75.6%
LiveCodeBench84.6%
SciCode42.9%
MATH-50099.4%
AIME95.7%
AIME 202594.3%
IFBench73.1%
τ²-Bench84.8%
τ-Bench Banking19.6%
Terminal-Bench35.2%
Terminal-Bench Hard32.6%
⚡ Speed110.5 tokens/sec
⏱ Latency91s to first token
💰 Blended price$3.438 / 1M tokens
📈 Value10.1 intelligence points per $
Benchmark data by Artificial Analysis

About this model

GPT-5 is a commercial AI model by OpenAI. The specifications below are tracked automatically: pricing is refreshed hourly from public list prices, so the numbers on this page reflect the current cost of using the model through its API.

Frequently asked questions

What is GPT-5?

GPT-5 is an AI language model from OpenAI. It is a proprietary model, available through an API. It scores 34.7 on the Artificial Analysis intelligence index.

Is GPT-5 free?

GPT-5 is not free: it costs $1.25 per million input tokens and $10 per million output tokens. Open-weight alternatives can be self-hosted at no per-token cost.

What is GPT-5 good at?

Independent benchmarks from Artificial Analysis give it GPQA 85.4%, MMLU-Pro 87.1%, Humanity's Last Exam 26.5%, Long Context Reasoning 75.6%, LiveCodeBench 84.6%, SciCode 42.9%, MATH-500 99.4%, AIME 95.7%, AIME 2025 94.3%, IFBench 73.1%, τ²-Bench 84.8%, τ-Bench Banking 19.6%, Terminal-Bench 35.2%, Terminal-Bench Hard 32.6%. It is particularly used for code generation.

How fast is GPT-5?

It generates about 110.5 tokens per second, with a median 91s delay before the first token. Measured independently by Artificial Analysis.

Open-source alternatives

Depending on your workload, an open-weight model that you can self-host may cut costs dramatically or remove per-token pricing entirely. Our comparison pages put this model side by side with the strongest open-source contenders.

GPT-5.5OpenAIGPT-5.6 SolOpenAIGPT-5.4OpenAIGPT-5.6 TerraOpenAIGPT-5.2OpenAIGPT-4.1OpenAI