Everything about GPT-5.4 nano

GPT-5.4 nano at a glance

Released on March 17, 2026, GPT-5.4 nano is one of the 16 OpenAI models tracked on this site. It is a closed model: you access it through an API, from OpenAI or one of the 36 providers listed on models.dev. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money. That makes it 7 months old as of October 22, 2026.

We file it under budget models (24 models in this category on the site).

Benchmark results

According to results published by Epoch AI (checked on October 22, 2026), GPT-5.4 nano has a capability index of 71.7 out of 100, computed on 3 benchmarks from our basket.

With only 3 benchmarks reported, it does not enter the public ranking, which requires at least 4 results, so its index should be read as partial.

• GPQA Diamond (PhD-level science questions): 78.5% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 87.8% — the best tracked model, GPT-5.5 Pro, reaches 100%
• FrontierMath (very hard research-level mathematics): 44.9% — the best tracked model, GPT-6 Astra, reaches 93.7%

How much does GPT-5.4 nano cost?

GPT-5.4 nano costs $0.20 per million input tokens and $1.25 per million output tokens (median of 36 providers, checked on October 22, 2026).

To put it in perspective: reading 20,000 tokens (about thirty pages) and writing 2,000 costs roughly $0.007; a thousand of those tasks, $6.5.

That is in line with budget models, whose median output price is $1.13.

To estimate your own budget, use the agent cost calculator.

Technical specifications

Its context window reaches 400,000 tokens, roughly 600 pages of text at 500 words per page: enough for a long report or several contracts at once. A single answer can run to 128,000 tokens.

It accepts as input: text and image. Its knowledge stops at August 31, 2025: beyond that, it needs web search or your documents.

It can call tools (functions, APIs) and return structured JSON output, which makes it a possible foundation for an AI agent.

When to choose it

Given its category, GPT-5.4 nano is mainly aimed at high volumes where every cent counts: sorting, information extraction, summaries, simple assistants.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

What could replace it?

In the same category, the models closest to GPT-5.4 nano are:

• Qwen3.6 Flash (Alibaba Cloud (Qwen), index 64.5) — see the comparison
• Gemini 3.1 Flash Lite (Google DeepMind, index 64.3) — see the comparison
• GPT-5.6 Luna (OpenAI, index 79.6) — see the comparison
• Qwen3.7 Flash (Alibaba Cloud (Qwen), index 63.7) — see the comparison