OpenAI: GPT-5.4 miniOfficial docs

OpenAI: GPT-5.4 mini

byOpenAI
Official docs

GPT-5.4 mini is a reasoning model from OpenAI released on Mar 17, 2026. It reads text and images and writes text, with a 400K token context window and up to 128K tokens per reply.

Show more

It costs $0.75 per million input tokens and $4.50 per million output tokens. Cached input bills at $0.075, 90% less than fresh input.

It supports tool calling, structured JSON output and prompt caching.

38 providers serve it, including Azure, Databricks and Vercel AI Gateway. The lowest input price is $0.375 per million tokens at Xpersona.

Modalities
In / out price
$0.75 / $4.50 per 1M
Context
400K
Max output
128K
Released
Mar 17, 2026
Knowledge cutoff
Aug 2025
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

GPT-5.4 mini pricing

USD, as listed on Nov 18, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$0.75 / 1M tokens
Output$4.50 / 1M tokens
Cached input (read)$0.075 / 1M tokens

GPT-5.4 mini providers

38 providers serve it, including Azure, Databricks and Vercel AI Gateway. The lowest input price is $0.375 per million tokens at Xpersona. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.

ProviderInput /MOutput /MCache read /MContextMax output
OpenAI First party$0.75$4.50$0.075400K128K
Azure$0.75$4.50$0.075400K128K
Databricks$0.75$4.50$0.075400K128K
Vercel AI Gateway$0.75$4.50$0.075400K128K
Xpersona$0.375$4$0.0375272K128K
Poe$0.6818$4.09$0.0682400K128K
302.AI$0.75$4.50$0.075400K128K
Abacus$0.75$4.50$0.075400K128K
AIHubMix$0.75$4.50$0.075400K128K
Azure Cognitive Services$0.75$4.50$0.075400K128K
Cloudflare AI Gateway$0.75$4.50$0.075128K128K
CommandCode$0.75$4.50$0.075400K128K

Showing 12 of 38 providers: the lab first, then the major clouds, then the cheapest resellers.

What GPT-5.4 mini costs per month

Pick a workload close to yours or type your own volumes.

GPT-5.4 mini per month
$73.13
Without caching
$104
Per request
$0.0024

Supported request parameters

What you can set when you call GPT-5.4 mini through an OpenAI compatible API.

  • Toolstools
  • Structured outputsstructured_outputs
  • Reasoningreasoning
  • Temperaturetemperature

Alternatives to GPT-5.4 mini

Models that take the same inputs and call tools, closest in price, cheaper ones first.

  • Reads text, images and files. Tool calling, structured output, reasoning. Served by 29 providers.

    by x-aiApr 17, 2026$1.25/M input tokens$2.50/M output tokens29 providers

  • Reads text, images and files. Tool calling, structured output, reasoning. Served by 12 providers.

    by x-aiMar 9, 2026$1.25/M input tokens$2.50/M output tokens12 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 40 providers.

    by googleSep 2, 20261.05M context$0.75/M input tokens$3.75/M output tokens40 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 27 providers.

    by googleJul 21, 2026$0.75/M input tokens$3.75/M output tokens27 providers

  • Reads text, images and files. Tool calling, structured output, reasoning. Served by 16 providers.

    by x-aiApr 16, 2026$1/M input tokens$2/M output tokens16 providers

  • Index 33.7

    Reads text and images. Tool calling, structured output, reasoning. Served by 71 providers.

    by qwenAug 14, 2026262K context$0.45/M input tokens$3.20/M output tokens71 providers

More from OpenAI

  • Reads text, images and files. Tool calling, structured output, reasoning. Served by 9 providers.

    by openaiNov 17, 2026$8/M input tokens$40/M output tokens9 providers

  • Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.

    by openaiNov 17, 2026$16/M input tokens$60/M output tokens2 providers

  • Reads text, images and files. Tool calling, structured output, reasoning. Served by 9 providers.

    by openaiNov 17, 2026$2/M input tokens$10/M output tokens9 providers

  • Reads text, images and files. Tool calling, structured output, reasoning. Served by 2 providers.

    by openaiNov 17, 2026$4/M input tokens$15/M output tokens2 providers

  • Generates images from text and images.

    by openaiOct 28, 2026

  • Generates images from text and images.

    by openaiOct 28, 2026

All OpenAI models

GPT-5.4 mini questions

How much does the GPT-5.4 mini API cost?

$0.75 per million input tokens and $4.50 per million output tokens, with cached input at $0.075. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of GPT-5.4 mini?

400,000 tokens of input, and it can write up to 128,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Which providers serve GPT-5.4 mini?

38 providers serve it, including Azure, Databricks and Vercel AI Gateway. The lowest input price is $0.375 per million tokens at Xpersona. Prices differ by host, so the Providers table on this page lists each one with its input and output price.

Does GPT-5.4 mini support tool calling?

Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.

Is GPT-5.4 mini open source?

No. OpenAI serves it through an API only, so you cannot download the weights or host it yourself.

When was GPT-5.4 mini released?

Mar 17, 2026, with training data up to Aug 2025.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Nov 18, 2026. The summary is written from these facts.