OpenAI: GPT-5.4 Nano
openai/gpt-5.4-nano
Access GPT-5.4 Nano from OpenAI using the Puter.js AI API.
Get Started// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "openai/gpt-5.4-nano"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "openai/gpt-5.4-nano"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
GPT-5.4 Nano is the smallest and cheapest model in the GPT-5.4 family, offering a 400k context window at just $0.20/1M input tokens. It excels at classification, data extraction, ranking, and coding sub-agent tasks, outperforming the previous GPT-5 Mini on SWE-Bench Pro (52.4% vs 45.7%). It's ideal for high-volume, low-latency workloads and as a fast sub-agent in multi-model architectures.
Context Window 400K
tokens
Max Output 128K
tokens
Input Cost $0.2
per million tokens
Output Cost $1.25
per million tokens
Input text, image
modalities
Tool Use Yes
Knowledge Cutoff Aug 31, 2025
Release Date Mar 19, 2026
Model Playground
Try GPT-5.4 Nano instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How GPT-5.4 Nano performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 81.7% |
| Humanity's Last Exam Cross-domain reasoning | 28.3% |
| SciCode Scientific programming | 47.2% |
| IFBench Instruction following | 75.9% |
| LCR Long-context reasoning | 76.7% |
| Terminal-Bench Hard Agentic terminal tasks | 42.4% |
| τ²-Bench Tool use / agents | 76.0% |
Scores sourced from Artificial Analysis.
Find other OpenAI models →
GPT Image 2.5 Flare
GPT Image 2.5 Flare is OpenAI's fast image generation and editing model in the GPT Image 2.5 family, released September 8, 2026 as the successor to GPT Image 2. It takes text and image input and returns generated or edited images. OpenAI reports it produces higher-quality output than GPT Image 2 at up to 50% lower latency, with improvements in lighting, texture, and consistency when editing from reference images. Within the GPT Image 2.5 family, Flare is the speed-oriented tier. OpenAI positions it as the default choice for creator and social content, product imagery, visual search, rapid prototyping, and high-volume generation, while the companion Sunburst model targets premium workflows that need tighter control over detailed edits. The API exposes quality levels low, medium, high, xhigh, max, and auto. At low quality and 1024x1024 resolution, an image costs $0.00588.
ImageGPT Image 2.5 Sunburst
GPT Image 2.5 Sunburst is an image generation and editing model from OpenAI, released September 8, 2026 as part of the GPT Image 2.5 family alongside a faster sibling model, GPT Image 2.5 Flare. It is built for precision editing workflows, with tighter control over edits, better subject preservation from reference images, and the ability to keep unrelated areas of an image unchanged across multiple edit turns. OpenAI positions it for production-ready campaign creative and polished product imagery, in contrast to Flare's focus on high-volume, everyday generation. Sunburst supports quality levels from low through max, plus auto. At low quality and 1024x1024 resolution, an image costs $0.00588. It runs slower than Flare, trading speed for editing precision.
ChatGPT-6 Astra
GPT-6 Astra is OpenAI's most capable model, released in September 2026 as the successor to GPT-5.6 Sol. It targets complex reasoning, coding, computer use, research, and document creation, taking text and image input over a 1,050,000-token context window and supporting tool calling. OpenAI reports Astra saturates FrontierMath Tier 4 at 97.6% and ARC-AGI-3 at 99.9%, and cuts its hallucination rate from 92% to 51% at max effort versus GPT-5.6 Sol. It is the first OpenAI model to reach the Critical cybersecurity level under OpenAI's Preparedness Framework, scoring 100% on ExploitBench versus 78.5% for GPT-5.6 Sol. Independent testing from Artificial Analysis puts Astra's Intelligence Index at 61.2, roughly level with GPT-5.6 Sol and behind Claude Fable 5.1's 65.7. Input costs $5 per million tokens and output $25 per million, 2.5 times GPT-5.6 Sol's rate.
Frequently Asked Questions
You can access GPT-5.4 Nano by OpenAI through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
GPT-5.4 Nano is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.2 |
| Output | $1.25 |
GPT-5.4 Nano was created by OpenAI and released on Mar 19, 2026.
GPT-5.4 Nano supports a context window of 400K tokens. For reference, that is roughly equivalent to 800 pages of text.
GPT-5.4 Nano can generate up to 128K tokens in a single response.
GPT-5.4 Nano has a knowledge cutoff date of Aug 31, 2025. This means the model was trained on data available up to that date.
GPT-5.4 Nano accepts the following input types: text, image. It produces: text.
Yes, GPT-5.4 Nano supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
GPT-5.4 Nano scores 21.2 on the Artificial Analysis Intelligence Index, outperforming 72% of tracked models. On coding, it scores 56.1 (outperforms 62% of models).
Yes — the GPT-5.4 Nano API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add GPT-5.4 Nano to your app for free
Developers can integrate GPT-5.4 Nano for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.