GPT-5.4 API

Input / 1M tokens$2.20~~$2.50~~

Output / 1M tokens$13.20~~$15.00~~

LLMOpenAI12% below official1M contextPrompt caching

Loading playground…

About GPT-5.4

GPT-5.4 by OpenAI is available on API Many from $2.20 per million input tokens and $13.20 per million output tokens, and you call it with the same API key you use for every other model.

It accepts OpenAI-style chat requests with streaming and tools, has a 1M context window and can return up to 12,800 tokens per response.

Prompt caching is supported: cached input tokens are billed at the lower cached rate shown in the price table.

You pay only for successful results: failed or rejected requests are refunded automatically, and every call is recorded in your console with its exact cost.

Related models

−12%

GPT-5gpt-5

LLMOpenAI128K contextPrompt caching

$1.10 in · $8.80 outTry it

−12%

GPT-5 (2025-08-07)gpt-5-2025-08-07

LLMOpenAI

$1.10 in · $8.80 outTry it

−12%

GPT-5 Chat Latestgpt-5-chat-latest

LLMOpenAI

$1.10 in · $8.80 outTry it

−12%

GPT-5 Codexgpt-5-codex

LLMOpenAICoding

$1.10 in · $8.80 outTry it

−12%

GPT-5 Minigpt-5-mini

LLMOpenAI128K contextPrompt caching

$0.22 in · $1.76 outTry it

−12%

GPT-5 Mini (2025-08-07)gpt-5-mini-2025-08-07

LLMOpenAI

$0.22 in · $1.76 outTry it

−12%

GPT-5 Nanogpt-5-nano

LLMOpenAI128K contextPrompt caching

$0.044 in · $0.352 outTry it

−12%

GPT-5 Nano (2025-08-07)gpt-5-nano-2025-08-07

LLMOpenAI

$0.044 in · $0.352 outTry it

Frequently asked questions

How much does the GPT-5.4 API cost?

GPT-5.4 starts at $2.20 per million input tokens and $13.20 per million output tokens on API Many. The price table on this page lists every tier; you are charged only for successful requests.

How do I call GPT-5.4?

Create an API key in the console, then send a request to /v1/chat/completions with "model": "gpt-5.4". The API tab has copy-ready examples in cURL, Python and Node.js.

Is this the official GPT-5.4 model?

Yes. Requests are forwarded to the model maker or an authorized channel with the same parameters, so the output matches the official API.

What happens if a request fails?

Failed, rejected or timed-out requests are not charged. Reserved balance is released automatically and the reason is shown in the call record.