# gpt-5-mini — API, Pricing & Context Window | Vivgrid

> Source: https://vivgrid.com/docs/models/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.

> **Scheduled retirement: November 11, 2026.** This model will no longer be available on Vivgrid after retirement. Migrate to [gpt-6-luna](/docs/models/gpt-6-luna) before that date.

`gpt-5-mini` is the compact, budget-friendly member of the GPT-5 family. It keeps a **272K-token context window** and function-calling support while delivering faster responses at a fraction of the flagship price.

Vivgrid geo-distributes `gpt-5-mini` across **AMER, EMEA, and APAC**, making it ideal for high-volume, latency-sensitive traffic anywhere in the world.

## Specifications

| Field | Value |
| --- | --- |
| Provider | OpenAI |
| Model ID | `gpt-5-mini` |
| Best for | General-purpose |
| Available on | Chat Completions |
| Context window | 272,000 tokens |
| Max output | 128,000 tokens |
| Modalities | Text, Image |
| Tool / function calling | Yes |
| Knowledge cutoff | 2024-05 |
| Acceleration | Geo-distributed — AMER, EMEA, APAC |

## Pricing

Pricing in USD per 1M tokens.

| Input | Cached input | Output |
| --- | --- | --- |
| $0.25 | $0.03 | $2.00 |

### 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 | $0.00900 |
| Warm prompt, 90% of the input served from cache | $0.00504 |


## API surfaces

The Vivgrid Console catalogs `gpt-5-mini` 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 |
| --- | --- | --- |
| Chat Completions | `/chat/completions` | Agent projects, where Vivgrid injects the model, system prompt and tools server-side, and Model API calls that name the model per request. |

## Quick start

Get an API key from the Vivgrid Console (https://console.vivgrid.com), then call `gpt-5-mini` 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-mini",
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'
```


## Ideal use cases

- High-throughput chat and agent backends
- Classification, extraction, and routing
- Cost-conscious tool-calling workflows
- Edge cases where latency beats maximum quality

## 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) — newer-generation mini
- [gpt-6.1-sol](/docs/models/gpt-6.1-sol) — balanced current-generation model