# gpt-5.4-nano — API, Pricing & Context Window

gpt-5.4-nano on Vivgrid: the smallest, most economical GPT-5.4 model with a 400K context window and image and PDF input for high-scale tasks.

`gpt-5.4-nano` is the smallest and most economical model in the GPT-5.4 family, built for massive-scale, latency-sensitive workloads. Despite its size it keeps a **400K-token context window** and supports image and PDF inputs.

Vivgrid serves it with geo-distributed acceleration across **AMER and EMEA**, so even the highest-volume pipelines stay fast and affordable.

## Specifications

|     |     |
| --- | --- |
| **Provider** | OpenAI |
| **Model ID** | `gpt-5.4-nano` |
| **Best for** | General-purpose |
| **Context window** | 400,000 tokens |
| **Max output** | 128,000 tokens |
| **Modalities** | Text, Image, Pdf |
| **Tool / function calling** | Yes |
| **Knowledge cutoff** | 2025-08 |
| **Acceleration** | ⚡ Geo-Distributed — AMER, EMEA |

## Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

| Input | Cached input | Output |
| --- | --- | --- |
| $0.20 | $0.02 | $1.25 |

## Quick start

Call `gpt-5.4-nano` through Vivgrid's unified, OpenAI-compatible endpoint. Get an API key from the [Vivgrid Console](https://console.vivgrid.com/).

```
curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4-nano",
    "messages": [\
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }\
    ],
    "stream": true
  }'
```

## Ideal use cases

- Very high-volume classification, tagging, and routing
- Lightweight assistants and autocomplete-style features
- Cost-sensitive preprocessing in larger agent pipelines
- Bulk document and image triage

## Related models

- [gpt-5.4-mini](/content/docs/models/gpt-5.4-mini/index.html) — a step up in quality
- [gpt-5.4](/content/docs/models/gpt-5.4) — the flagship 5.4 model
- [gpt-5-mini](/content/docs/models/gpt-5-mini/index.html) — prior-generation small model