# gpt-5-chat — API, Pricing & Context Window

gpt-5-chat on Vivgrid: a conversation-tuned GPT-5 model with a 128K context window and image input, accessed through one unified API.

`gpt-5-chat` is the conversation-optimized variant of GPT-5, tuned for natural, helpful multi-turn dialogue. With a **128K-token context window** and image input, it's a good fit for product chatbots and assistant experiences.

On Vivgrid, `gpt-5-chat` is available through the same OpenAI-compatible endpoint and unified API key as every other model, so you can A/B it against alternatives without code changes.

## Specifications

|     |     |
| --- | --- |
| **Provider** | OpenAI |
| **Model ID** | `gpt-5-chat` |
| **Best for** | General-purpose |
| **Context window** | 128,000 tokens |
| **Modalities** | Text, Image |
| **Tool / function calling** | Yes |
| **Knowledge cutoff** | 2024-10 |
| **Acceleration** | 🌐 Global (Centralized) |

## Pricing

Pricing for `gpt-5-chat` matches the provider's published rates. See live pricing in the [Vivgrid Console](https://console.vivgrid.com/).

## Quick start

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

## [Ideal use cases](/content/docs/models/gpt-5-chat#ideal-use-cases/index.html)

- Customer-facing chat assistants
- Conversational product experiences
- Multi-turn support and Q&A bots
- Scenarios prioritizing fluent dialogue over deep tool use

## [Related models](/content/docs/models/gpt-5-chat#related-models/index.html)

- [gpt-5](/content/docs/models/gpt-5/index.html) — the general-purpose GPT-5 model
- [gpt-5-mini](/content/docs/models/gpt-5-mini/index.html) — smaller, faster sibling
- [gpt-5.2](/content/docs/models/gpt-5.2) — newer general-purpose model

[gpt-5-mini

gpt-5-mini on Vivgrid: a fast, affordable GPT-5 model with a 272K context window, function calling, and three-region acceleration.](/content/docs/models/gpt-5-mini/index.html) [gpt-4.1

gpt-4.1 on Vivgrid: OpenAI's GPT-4.1 with a ~1M-token context window and image input, available through a single unified API.](/content/docs/models/gpt-4.1)