What is OpenAI: GPT-5.4 Nano's context window?

OpenAI: GPT-5.4 Nano supports a context window of 400,000 tokens, allowing you to process large documents and maintain long conversations.

How to use OpenAI: GPT-5.4 Nano API via Ofox?

Simply set your base URL to https://api.ofox.ai/v1 and use your Ofox API key. The API is OpenAI-compatible — just change the base URL and API key in your existing code.

OpenAI: GPT-5.4 Nano

Name: OpenAI: GPT-5.4 Nano
Brand: openai
Price: 0.19999999999999998 USD
Availability: InStock

Chat-20%

openai/gpt-5.4-nano

Compare Try in Playground Get started

GPT-5.4 Nano is the lightest and most cost-efficient member of the GPT-5.4 family, released on 2026-03-17 and optimized for speed-critical, high-volume tasks such as classification, data extraction, ranking, and sub-agent execution. It accepts text and image input and supports reasoning, tool use (function calling), prompt caching, and web search. Context: 400K tokens, output: 128K. Available via OpenAI and Anthropic protocols.

Context Window

400K

Max Output Tokens

128K

Released

2026-03-17

Capabilities

VisionFunction CallingReasoningPrompt CachingWeb Search

Available Providers

Azure

Supported Protocols

openaianthropic

Providers

Azureprovider.type: "azure_foundry"

-20%

Input Tokens

$0.16/M

$0.2/M

Output Tokens

$1/M

$1.25/M

Cache Read

$0.016/M

$0.02/M

Output Image

$25.6/M

$32/M

Web Search

$0.035/R

Protocols

openai/v1/chat/completions/v1/responses

anthropic

Playground

Open in OfoxChat

Code Examples

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ofox.ai/v1",
    api_key="YOUR_OFOX_API_KEY",
)

response = client.chat.completions.create(
    model="openai/gpt-5.4-nano",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)

Uptime & Status

Benchmarks

LMArena ↗Evaluated as gpt-5.4-nano-high

OpenAI: GPT-5.4 Nano scores 1404 in the Overall category of the LMArena text leaderboard (style control), ranking #121 of 374 models based on 53,078 human preference votes (updated 2026-07-12).

Benchmark scores for gpt-5.4-nano-high on LMArena
Category	Arena Score	95% CI	Rank	Votes
Overall	1404	1400–1408	#121 of 374	53,078
Hard Prompts	1423	1419–1428	#119 of 374	34,785
Coding	1461	1455–1468	#102 of 369	14,887
Math	1427	1415–1439	#84 of 362	2,801
Creative Writing	1337	1329–1345	#159 of 372	8,601
Instruction Following	1388	1382–1394	#127 of 374	17,846
Chinese	1422	1409–1435	#130 of 344	2,723

Source: LMArena · CC BY 4.0 · Updated 2026-07-12 · Methodology ↗ · Ranks compare models within each category of the LMArena text leaderboard (style control). Scores come from third-party human preference evaluations, not from OFOX.