CrossModel
GPT-5.4 Nano
openai/gpt-5.4-nano
Back to model catalog

OpenAI · Model guide

GPT-5.4 Nano

Compare
openai/gpt-5.4-nano

GPT-5.4 Nano is the smallest GPT-5.4 model. It keeps reasoning, structured output and broad tool support for latency-sensitive classification, extraction, ranking and simple coding subagents.

Modalities
TextImageText
Context
400K
Max output
128K
Price / 1M tokens
$ 0.20in$ 1.25out
StreamingTool callingJSON outputImage inputThinking mode

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorThe cheapest GPT-5.4-class model for simple high-volume tasks.source

Best for

  • Classification and extraction · OpenAI recommends Nano where speed and cost matter most, including classification and data extraction.(vendor claim)source

  • Ranking and simple subagents · Designed for ranking and narrower supporting tasks.(vendor claim)source

Neighbouring models
  • openai/gpt-5.4-ministronger —Use Mini when computer use or harder coding is required.
  • openai/gpt-5.6-lunasuccessor —Luna is the newer cost-sensitive tier with a much longer context window.
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 0.20
Output$ 1.25
Cache read$ 0.020
Cache write$ 0.20
Estimate a request
$ 0.0045
Estimated cost per request
10.0K × $ 0.20
+ 2.0K × $ 1.25
≈ $ 4.50 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
400.0K tokens
Max output
128.0K tokens
Input / output modalities
Text + Image → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· always on
Reasoning effort
none · low · medium · high · xhigh
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specsdevelopers.openai.comCapabilitiesdevelopers.openai.com 1openai.com 2

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding
  • Terminal-Bench 2.0
    pass_rate·OpenAI · 2026-03-17effort xhighsetup not fully disclosed
    46.3%
Coding
  • SWE-Bench Pro (Public)
    pass_rate·OpenAI · 2026-03-17effort xhighsetup not fully disclosed
    52.4%
Computer use
  • OSWorld-Verified
    success_rate·OpenAI · 2026-03-17effort xhighsetup not fully disclosed
    39%
Long context
  • OpenAI MRCR v2 8-needle 128K–256K
    accuracy·OpenAI · 2026-03-17effort xhighsetup not fully disclosed
    33.1%
Multimodal reasoning
  • MMMU Pro (no tools)
    accuracy·OpenAI · 2026-03-17effort xhighsetup not fully disclosed
    66.1%
Reasoning
  • Humanity's Last Exam Full (with tools)
    accuracy·OpenAI · 2026-03-17effort xhighsetup not fully disclosed
    37.7%
Scientific reasoning
  • GPQA Diamond
    accuracy·OpenAI · 2026-03-17effort xhighsetup not fully disclosed
    82.8%
Tool use
  • Toolathlon
    score·OpenAI · 2026-03-17effort xhighsetup not fully disclosed
    35.5%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is GPT-5.4 Nano?
GPT-5.4 Nano is available on CrossModel as openai/gpt-5.4-nano. It has a 400K-token context window and can return up to 128K tokens per request.
How much does GPT-5.4 Nano cost?
Currently $ 0.20 per 1M input tokens and $ 1.25 per 1M output tokens. Cached input is billed at $ 0.020 per 1M.
Does GPT-5.4 Nano support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.