# GPT-6.1 Sol is now available in AI Gateway

> Call OpenAI's GPT-6.1 Sol through AI Gateway with your ngrok access key and credits.

- Date: 2026-10-01
- Shipped by: Jarod Clark
- Products: AI Gateway
- URL: https://ngrok.com/changelog/ai-gateway-gpt-6-1-sol

AI Gateway now supports **GPT-6.1 Sol** from **OpenAI**.

Call it as `openai/gpt-6.1-sol`. It's a built-in model with a 1M token context window, so your ngrok access key and credits cover inference and you don't need your own OpenAI key. Input tokens cost $2.00 per million and output tokens cost $10.00 per million.

Point an OpenAI SDK client at AI Gateway to try the model in your application and inspect its requests in one place.

Check [**Models**](https://app.ngrok.ai/models) to confirm current prices and supported request formats. Costs depend on the tokens your application sends and receives.

![AI Gateway Models page with the search filtered to gpt-6.1-sol, showing a single built-in row for openai/gpt-6.1-sol with a 1M context window, a $2.00 per million input token price, and a $10.00 per million output token price.](https://ngrok.com/blog-assets/images/2026-10-01-ai-gateway-gpt-6-1-sol/gpt-6-1-sol-models.png)

## Get started

[Create an ngrok account or sign in](https://app.ngrok.ai/). Create an [**access key**](https://app.ngrok.ai/keys) that allows OpenAI and GPT-6.1 Sol, and confirm your account has credits.

Optionally, try GPT-6.1 Sol in the [playground](https://app.ngrok.ai/playground).

Follow the [**setup guide**](https://app.ngrok.ai/getting-started) and select **OpenAI** and **TypeScript**.

Install the OpenAI SDK and TypeScript runner:

```bash
npm install openai && npm install --save-dev tsx
```

Save your ngrok access key in `.env.local`. Keep this file out of version control:

```dotenv
AI_GATEWAY_API_KEY=your_access_key_here
```

Use an ES module project (`"type": "module"` in `package.json`) for top-level `await`. Save this example as `index.ts`:

```typescript
import OpenAI from "openai";

const client = new OpenAI({
	baseURL: "https://gateway.ngrok.ai/v1",
	apiKey: process.env.AI_GATEWAY_API_KEY,
});

const response = await client.chat.completions.create({
	model: "openai/gpt-6.1-sol",
	messages: [{ role: "user", content: "Explain HTTP retries in two sentences." }],
});

console.log(response.choices[0]?.message.content);
```

Run the example from your project directory to print the response:

```bash
node --env-file=.env.local --import tsx index.ts
```

Open [**Logs**](https://app.ngrok.ai/activity), find the request you just sent, and inspect its model, provider, status, token usage, and cost.