# gpt-5.4 — API, Pricing & Context Window | Vivgrid

> Source: https://vivgrid.com/docs/models/gpt-5.4

Use OpenAI's gpt-5.4 on Vivgrid: a 1.05M-token coding model with three-region acceleration (AMER, EMEA, APAC) and an OpenAI-compatible API.

`gpt-5.4` is a high-capability OpenAI coding model that balances frontier-level quality with a more accessible price than `gpt-5.5`. Its **1.05M-token context window** comfortably holds large codebases, design docs, and long agent histories.

On Vivgrid it has the **widest acceleration footprint** of the GPT-5 family — geo-distributed across **AMER, EMEA, and APAC** — making it a strong default for globally distributed teams and agents.

## Specifications

| Field | Value |
| --- | --- |
| Provider | OpenAI |
| Model ID | `gpt-5.4` |
| Best for | Coding |
| Available on | Vibe coding |
| Context window | 1,050,000 tokens |
| Max output | 128,000 tokens |
| Modalities | Text, Image |
| Tool / function calling | Yes |
| Knowledge cutoff | 2025-08 |
| Acceleration | Geo-distributed — AMER, EMEA, APAC |

## Pricing

Pricing in USD per 1M tokens.

| Input | Cached input | Output |
| --- | --- | --- |
| $2.50 | $0.25 | $15.00 |

### What one request costs

The rates above applied to a 20K-token prompt with a 2K-token reply — a typical single agent turn, small enough that every request is billed at the base rate.

| Request | Cost |
| --- | --- |
| Cold prompt, nothing cached | $0.0800 |
| Warm prompt, 90% of the input served from cache | $0.0395 |


## API surfaces

The Vivgrid Console catalogs `gpt-5.4` on one surface, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

| Surface | Primary endpoint | Use it for |
| --- | --- | --- |
| Vibe coding | `/chat/completions` | Coding CLIs and IDE agents that drive the model themselves — point the tool at Vivgrid and keep your own loop. |

## Quick start

Get an API key from the Vivgrid Console (https://console.vivgrid.com), then call `gpt-5.4` directly.

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


## Ideal use cases

- Production coding agents that need frontier quality at moderate cost
- Teams with users across the Americas, Europe, and Asia-Pacific
- Long-context analysis and refactoring of large repositories
- Tool-calling agents requiring reliable, structured outputs

## Related models

- [gpt-6-astra](/docs/models/gpt-6-astra) — the gpt-6 generation flagship
- [gpt-5.6-luna](/docs/models/gpt-5.6-luna) — a faster, cheaper current-generation sibling
- [gpt-6.1-sol](/docs/models/gpt-6.1-sol) — the balanced gpt-6 coding model