> ## Documentation Index
> Fetch the complete documentation index at: https://docs.corbits.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI

> Access the full OpenAI API through Corbits — GPT models, embeddings, images, and more

## Overview

The OpenAI proxy gives you pay-per-request access to the full OpenAI API — chat completions, embeddings, image generation, audio, fine-tuning, and more. No OpenAI account or API key required.

|                    |                                  |
| ------------------ | -------------------------------- |
| **Proxy URL**      | `https://openai.api.corbits.dev` |
| **Proxy ID**       | `61`                             |
| **Default price**  | \$0.01 per request               |
| **Pricing scheme** | Exact                            |

## Quick start

Install the payment SDK and make a chat completion request:

```javascript theme={null}
import { payer } from "@faremeter/rides";

// Load your Solana keypair
await payer.addLocalWallet(process.env.PAYER_KEYPAIR);

const response = await payer.fetch("https://openai.api.corbits.dev/v1/chat/completions", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "gpt-4o",
    messages: [{ role: "user", content: "Hello from Corbits!" }],
  }),
});

const data = await response.json();
console.log(data.choices[0].message.content);
```

## Key endpoints

The proxy exposes the full OpenAI API. Here are the most commonly used endpoints:

| Endpoint                   | Description                                         |
| -------------------------- | --------------------------------------------------- |
| `/v1/chat/completions`     | Generate chat completions (GPT-4o, GPT-4, etc.)     |
| `/v1/responses`            | Create model responses with tool use and web search |
| `/v1/embeddings`           | Generate text embeddings                            |
| `/v1/images/generations`   | Generate images (DALL-E, GPT Image)                 |
| `/v1/audio/speech`         | Text-to-speech                                      |
| `/v1/audio/transcriptions` | Speech-to-text (Whisper)                            |
| `/v1/models`               | List available models                               |
| `/v1/completions`          | Legacy text completions                             |
| `/v1/moderations`          | Content moderation                                  |
| `/v1/fine_tuning/jobs`     | Fine-tuning management                              |

<Note>
  The proxy supports 90+ endpoints covering the full OpenAI API surface. Use the Discovery API to get the complete list.
</Note>

## Discover this merchant

Query the Discovery API to get live details about this proxy:

```bash theme={null}
# Search for this proxy
curl "https://api.corbits.dev/api/v1/search?q=openai"

# Get proxy details
curl "https://api.corbits.dev/api/v1/proxies/61"

# List all endpoints with pricing
curl "https://api.corbits.dev/api/v1/proxies/61/endpoints"

# Get the full OpenAPI spec
curl "https://api.corbits.dev/api/v1/proxies/61/openapi"
```

## Notes

* Requests are proxied directly to the OpenAI API. Request and response formats match the [OpenAI API reference](https://platform.openai.com/docs/api-reference).
* Payment is handled at the proxy layer via x402 — the `@faremeter/rides` SDK manages the challenge/response cycle automatically.
* Pricing is per-request at the proxy level. Upstream token-based costs from OpenAI are included in the proxy price.