---
title: OpenAI-Compatible API Quickstart — GPT-5.6 on One Key
description: "Run GPT-5.6 models on apiToken.sale through the OpenAI-compatible API — Responses and Chat Completions with SSE streaming, one sk-pool key and balance shared with Claude, at 60–70% off."
url: https://apitoken.sale/docs/learn/openai-api-quickstart
language: en
---

# OpenAI-compatible API quickstart: Responses and Chat Completions

Your sk-pool key is not Claude-only. The same key and prepaid balance also serve the GPT-5 line through an OpenAI-compatible endpoint — standard Responses and Chat Completions calls, official OpenAI SDKs, SSE streaming, and the same 60–70% discount.

## Three steps to your first GPT call

1. Create a free account and generate one API key (it looks like sk-pool-…) — the same key already covers Claude models too.
2. Point your client at https://openai.api.apitoken.sale/v1 and authenticate with Authorization: Bearer — not x-api-key; that header belongs to the Anthropic surface.
3. Confirm the enabled models with GET /v1/models, then send a Responses request.

```
curl https://openai.api.apitoken.sale/v1/responses \
  -H "Authorization: Bearer $APITOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-sol",
    "input": "Reply with exactly: connected"
  }'
```

## Use the official OpenAI SDK

The official SDKs work unchanged — only base_url and the key change. Keep the key in a server-side environment variable in production.

```
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["APITOKEN_API_KEY"],
    base_url="https://openai.api.apitoken.sale/v1",
)

response = client.responses.create(
    model="gpt-5.6-sol",
    input="Reply with exactly: connected",
)
print(response.output_text)
```

Chat Completions is served on the same host if your client expects it — the model ID and key stay the same.

```
completion = client.chat.completions.create(
    model="gpt-5.6-sol",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
```

## Which GPT models are available

The served set is pinned and priced in the engine; GET /v1/models is always the live answer. Today the line covers three GPT-5.6 tiers and two previous-generation models:

| Model ID | Tier | Official in / out ($ per 1M) | Cached input |
| --- | --- | --- | --- |
| gpt-5.6-sol (alias: gpt-5.6) | Flagship | $5 / $30 | $0.50 |
| gpt-5.6-terra | Balanced | $2.50 / $15 | $0.25 |
| gpt-5.6-luna | Fast | $1 / $6 | $0.10 |
| gpt-5.5 | Previous flagship | $5 / $30 | $0.50 |
| gpt-5.4 | Previous balanced | $2.50 / $15 | $0.25 |

- Reasoning effort is adjustable per request — none through xhigh on every model, plus max on the GPT-5.6 line.
- Every model accepts text and image input and streams over SSE on both Responses and Chat Completions.
- Requests above 272K input tokens bill at OpenAI long-context rates: 2× input and 1.5× output on the whole request.
- Your B2C discount applies here exactly as it does to Claude usage — one balance, one tier, 60–70% off official spend.

[Full per-model specs and discounted prices](/models)

## What the endpoint does and does not cover

This is an independent OpenAI-compatible service, not the OpenAI Platform. It deliberately serves text generation only: model discovery, Responses, and Chat Completions with streaming and image input. Audio, files, realtime, assistants, batches and fine-tuning are not available.

> Errors come in the OpenAI envelope — {"error":{"message","type","param","code"}}. A 401 means the key or the auth header is wrong (use Bearer, not x-api-key), a 402 means the shared prepaid balance needs a top-up, and a 404 means the model ID is not enabled — check GET /v1/models.

## Frequently asked questions

### Does the same key really work for Claude and GPT?

Yes. One sk-pool key and one prepaid balance cover both surfaces: the Anthropic Messages API at api.apitoken.sale for Claude models and the OpenAI-compatible API at openai.api.apitoken.sale/v1 for GPT models. The discount is shared too.

### Which auth header does the OpenAI-compatible endpoint use?

Authorization: Bearer sk-pool-…. The x-api-key header is only for the Anthropic surface — sending it to the OpenAI endpoint returns a 401.

### Responses or Chat Completions?

Both are served with SSE streaming. Use Responses for new code and the official SDKs; Chat Completions works for clients and frameworks that expect the classic shape.

### How is GPT usage billed?

Per token at official OpenAI rates — including cached-input and long-context pricing — then your active 60–70% B2C discount is subtracted before the charge touches your prepaid balance, exactly like Claude usage.

---
Get a key: https://apitoken.sale/register
More guides: https://apitoken.sale/docs/learn