We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
OpenAI: GPT-5.4 Nano
openai/gpt-5.4-nanoTry OpenAI: GPT-5.4 Nano now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
OpenAI: GPT-5.4 Nano at a glance
- Input price is 56% lower than the median of 434 Text models.
- Context window of 400,000 tokens, enough for long documents and multi-turn conversations.
- Supports tool (function) calling for agents and integrations.
- Supports structured JSON output with a schema.
- Supports reasoning effort control.
- Accepts images as input (vision).
- A typical request (1,000 input / 500 output tokens) costs about $0.00289.
About OpenAI: GPT-5.4 Nano
GPT-5.4 Nano is a text model from OpenAI, positioned as the most lightweight and cost-efficient variant of the GPT-5.4 family. It is built for speed-critical and high-volume tasks, and it carries a knowledge cutoff of 2025-08-31. If you are choosing between members of the GPT-5.4 line, this is the one aimed at low-latency work rather than maximum capability.
The model accepts text, image and file inputs, and it returns text only. Its context window is 400,000 tokens, with a maximum output of 128,000 tokens, so long documents and large image sets can be handled in a single request without chunking. Because output is text, any structured result you need has to be expressed as text, which the model can do through its structured output support.
Those capabilities point to a fairly specific set of uses. High-volume classification, extraction and tagging jobs fit well, since the model is designed for throughput and low latency. Image input makes it usable for tasks such as reading screenshots, scanned forms or diagrams and returning a text summary or transcription. The large context window suits long-document question answering, summarisation and multi-file analysis where you would rather pass the source material directly than build a retrieval layer. Tool calling and structured outputs make it a reasonable fit for agent-style pipelines and for steps that must feed parsed data into downstream code.
You call it through api14's OpenAI-compatible API using the model id "openai/gpt-5.4-nano". The supported request parameters are include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools and verbosity. In practice that means you can cap output length, control how much reasoning effort the model spends, request a specific response format or structured output, set a seed for reproducibility, and pass tools with a tool_choice to drive function calling. Reasoning-related parameters let you decide whether reasoning content is surfaced and how verbose the model's output is.
The main thing to weigh is the trade-off implied by its positioning: it is the lightweight, cost-efficient member of the family, optimised for speed and volume. If a task depends on the strongest reasoning the GPT-5.4 family can offer, a larger sibling is likely the better choice, and Nano is best kept for the high-volume, latency-sensitive work it was designed for.
How to call the OpenAI: GPT-5.4 Nano API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "openai/gpt-5.4-nano".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "openai/gpt-5.4-nano",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsverbositySpecifications
- Context length
- 400,000
- Max output
- 128,000
- Input
- file, image, text
- Output
- text
- Knowledge cutoff
- 2025-08-31
Requests on api14 · last 7 days
OpenAI: GPT-5.4 Nano: frequently asked questions
- How much does the OpenAI: GPT-5.4 Nano API cost?
- OpenAI: GPT-5.4 Nano costs Input $0.70 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of OpenAI: GPT-5.4 Nano?
- OpenAI: GPT-5.4 Nano reads up to 400,000 tokens per request: prompt, history and documents together. It writes up to 128,000 output tokens per response.
- What can OpenAI: GPT-5.4 Nano do?
- OpenAI: GPT-5.4 Nano accepts file, image, text and returns text. It supports tool calling, structured JSON output, reasoning effort control.
- How do I call OpenAI: GPT-5.4 Nano from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "openai/gpt-5.4-nano". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to OpenAI: GPT-5.4 Nano?
- Comparable Text models at a similar price: DeepSeek: DeepSeek V3 0324, Z.ai: GLM Latest, DeepSeek: DeepSeek V4.1 Flash. Each runs through the same API key, so switching is one string.
OpenAI: GPT-5.4 Nano community
New topicThis community has no topics yet. Open the first one about OpenAI: GPT-5.4 Nano.