# gpt-4.1 — API, Pricing & Context Window | Vivgrid

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

`gpt-4.1` is OpenAI's refined GPT-4-generation model, notable for its very large **~1.05M-token context window** and strong instruction following. It remains a dependable choice for long-document workflows and established integrations.

Vivgrid serves `gpt-4.1` through its unified, OpenAI-compatible endpoint, so you can keep proven prompts running while routing through one API key and billing surface.

## Specifications

| Field | Value |
| --- | --- |
| Provider | OpenAI |
| Model ID | `gpt-4.1` |
| Best for | General-purpose |
| Available on | Chat Completions |
| Context window | 1,047,576 tokens |
| Modalities | Text, Image |
| Tool / function calling | Yes |
| Knowledge cutoff | 2024-05 |
| Acceleration | Global (centralized) |

## Pricing

Pricing in USD per 1M tokens.

| Input | Cached input | Output |
| --- | --- | --- |
| $2.00 | $0.50 | $8.00 |

### 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 | $0.0560 |
| Warm prompt, 90% of the input served from cache | $0.0290 |


## API surfaces

The Vivgrid Console catalogs `gpt-4.1` 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-4.1` directly.

```bash
curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'
```


## Ideal use cases

- Long-document analysis and summarization
- Stable production integrations built on GPT-4.x
- Instruction-following and structured extraction
- Workloads needing a very large context at GPT-4 pricing

## Related models

- [gpt-6-astra](/docs/models/gpt-6-astra) — the gpt-6 generation flagship
- [gpt-6.1-sol](/docs/models/gpt-6.1-sol) — current balanced GPT model
- [gpt-5.6-luna](/docs/models/gpt-5.6-luna) — cheaper modern alternative