GPT-5.4 Nano
VerifiedOpenAI's compact multimodal model for long-context file and image tasks.
About GPT-5.4 Nano
Built as a nano-scale release, the model focuses on efficient multimodal processing. It integrates files, images, and text in a single 400,000-token context. Closed weights keep the architecture proprietary while supporting broad input variety.
Strengths center on retaining coherence across lengthy mixed-media inputs. Typical usage includes document analysis that pairs visual elements with extended textual content. Developers apply it where compact deployment and high context capacity are priorities.
Capabilities
How GPT-5.4 Nano compares
GPT-5.4 Nano (striped bar) vs other multimodal on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · GPT-5.4 Nano ranks #23 of 100
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long multimodal document review
GPT-5.4 Nano processes up to 400000 tokens of combined text and images, making it suitable for analyzing lengthy reports that include embedded charts, diagrams, and photographs.
Extended video frame analysis
Its multimodal design supports ingesting long sequences of video frames alongside transcripts, enabling coherent summarization across extended footage.
Large-scale research synthesis
The model integrates text passages, data tables, and visual elements from multiple sources within a single 400000-token context for cross-referenced insights.
Strengths & limitations
Strengths
- +Very large 400k token context
- +Handles file, image, and text inputs
- +Multimodal flexibility
Limitations
- –Nano size may limit depth on complex tasks
- –No audio or video modalities
Pricing by provider
Live per-provider pricing & uptime, routed via OpenRouter. Prices are USD per 1M tokens.
| Provider | Input /1M | Output /1M | Context | Uptime |
|---|---|---|---|---|
| Azure | $0.20 | $1.25 | 400K | 100.0% |
| OpenAI | $0.20 | $1.25 | 400K | 81.2% |
Cost calculator
Estimate what GPT-5.4 Nano would cost for your usage.
Based on GPT-5.4 Nano's $0.20/1M input · $1.25/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "openai/gpt-5.4-nano",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: openai/gpt-5.4-nano
Editor's verdict
GPT-5.4 Nano is OpenAI's proprietary multimodal with a 400K-token context window.
At $1.25 per 1M output tokens, it is mid-priced for its class, served by 2 providers.
It is available through OpenAI's API and aggregators like OpenRouter.
Best suited to very large 400k token context and handles file, image, and text inputs.
Frequently asked questions
The model supports a context length of 400000 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other GPT models
Sibling versions in the GPT family from OpenAI.
Similar models
Other multimodal worth comparing.