# gpt-5 — API, Pricing & Context Window

gpt-5 on Vivgrid: OpenAI's GPT-5 model with a 272K context window, function calling, and three-region geo-distributed acceleration.

`gpt-5` is OpenAI's foundational GPT-5 model, a reliable all-rounder for reasoning, coding assistance, and agent workloads. Its **272K-token context window** covers most long-context needs, and it supports robust function calling.

On Vivgrid, `gpt-5` enjoys one of the widest acceleration footprints — geo-distributed across **AMER, EMEA, and APAC** — for consistently low latency worldwide.

## Specifications

|     |     |
| --- | --- |
| **Provider** | OpenAI |
| **Model ID** | `gpt-5` |
| **Best for** | General-purpose |
| **Context window** | 272,000 tokens |
| **Max output** | 128,000 tokens |
| **Modalities** | Text, Image |
| **Tool / function calling** | Yes |
| **Knowledge cutoff** | 2024-09 |
| **Acceleration** | ⚡ Geo-Distributed — AMER, EMEA, APAC |

## Pricing

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

| Input | Cached input | Output |
| --- | --- | --- |
| $1.25 | $0.125 | $10.00 |

## Quick start

Call `gpt-5` 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",
    "messages": [\
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }\
    ],
    "stream": true
  }'
```

## Ideal use cases

- General-purpose agents and chat assistants
- Tool-calling workflows that need dependable structured output
- Globally distributed deployments
- A stable baseline before adopting newer 5.x models

## Related models

- [gpt-5.1](/content/docs/models/gpt-5.1) — the next iteration with audio input
- [gpt-5-mini](/content/docs/models/gpt-5-mini/index.html) — smaller, cheaper sibling
- [gpt-5.4](/content/docs/models/gpt-5.4) — current high-capability model