Skip to content
ChatGPT API
EN
Drop-in ChatGPT API · pay-as-you-go

Buy ChatGPT API Access

Third-party ChatGPT API, drop-in compatible, pay-as-you-go, 20% cheaper than official, free quick start. Point your existing integration at our endpoint and ship.

Sign upView pricing
  • 20% below official pricing
  • Pay with crypto
  • No subscription · credits never expire
api.chatgpt-api.devLive
Modelinput / 1M
  • gpt-5.5$5.00$4.00
  • gpt-5.4-pro$30.00$24.00
  • gpt-5.3-codex$1.75$1.40
base_urlapi.chatgpt-api.dev
keysk-•••

Free test bonus

New accounts get a $2.50 test balance after sign-up. Try the gateway before buying credits.

Start with credits

How it works

Generate a key. Change one URL. Done.

Integration takes less than a minute.

1. Create an account

After you register, a $2.50 welcome bonus is credited to your balance so you can start testing any model right away.

2. Generate an API key

Create a ChatGPT API key from your dashboard. Top up your balance with crypto whenever you need it.

3. Point to our endpoint

Swap your base URL for our endpoint and keep using the SDK you already have. Every request shows up in your dashboard with token-level detail.

Compatible with both the official and OpenAI API formats

No refactor required — just point your existing integration to our endpoint. The same requests, headers, and streaming you already use keep working unchanged.

Set the base URL to https://api.chatgpt-api.dev/v1 and reuse your existing key handling.

request.ts
// Point your existing SDK at our endpoint
const client = new OpenAI({
  baseURL: "https://api.chatgpt-api.dev/v1",
  apiKey: process.env.OPENAI_API_KEY,
});

const response = await client.responses.create({
  model: "gpt-5.5",
  input: "Is a hot dog a sandwich?",
});

console.log(response.output_text);

Connect once. Work anywhere.

One key and one balance work across every tool on the list. Each comes with a short setup guide.

  • Cursor
  • Claude Code
  • Copilot
  • Codex
  • Cline
  • Open Code
  • Continue
  • Aider
  • Zed
  • OpenAI SDK

Pricing

Simple usage-based pricing, 20% cheaper

We are cheaper than the official ChatGPT (OpenAI) rates. No subscription. Credits never expire.

Buy discounted credits once
Buy discounted credits once, then spend them only when API requests run. Nothing is billed while you are idle.
Spend only on real requests
Every request is visible in your dashboard with token-level detail, so you always know exactly where your credits go.
No subscription, no expiry
There is no monthly fee and your credits never expire. Pay as you go and top up with crypto.
20% off official
−20%vs. official

Pricing mirrors official per-token rates, minus 20%.

Start with free credits

FAQ

Frequently asked questions

Everything about pricing, models, keys and setup.

How much does the ChatGPT API cost?

The ChatGPT API is pay-as-you-go and priced 20% below the official per-token list price. There is no subscription and no minimum spend — you buy credits once and they are only consumed when a request actually runs. Every request is metered at token level in your dashboard, so a small project can cost just a few cents. Pricing mirrors the official OpenAI per-token rates exactly, minus 20%, on both input and output tokens, and cached input is billed at the same discounted ratio. Because billing is usage-based rather than seat- or tier-based, your costs fall to near zero while your app is idle and scale up smoothly as traffic grows. You can see the full per-model breakdown on the pricing page and track spend in real time from your dashboard.

Is the ChatGPT API free?

There is a free quick start so you can generate a key and send your first requests without paying. Beyond the free quota you simply top up your balance with crypto. There is no subscription, and credits you buy never expire.

Which models are available?

You get drop-in access to all the latest OpenAI models — such as GPT-5.5, GPT-5.4-pro and GPT-5.3-codex — plus Claude models, through the official OpenAI format. Because we are API-format compatible, the model names you already use keep working. You pass the model ID in the standard `model` field of your request, exactly as with the official API, so switching between models is a one-line change. The OpenAI lineup covers flagship, mini, nano, pro and Codex variants for different speed-versus-quality trade-offs, while Claude models such as Claude Opus 4.8, Sonnet 4.6 and Haiku 4.5 are available for coding and agentic work. The full list of model IDs, with a short note on when to use each, is on the Models page in the docs.

Which model is best for coding?

For the hardest coding, refactoring and agentic tasks, gpt-5.5 is the strongest choice — or gpt-5.5-pro when you need maximum capability. gpt-5.3-codex is tuned specifically for code and pairs well with Codex CLI, Cursor and GitHub Copilot. For faster, cheaper day-to-day coding and high-volume completions, gpt-5.4-mini and gpt-5.4-nano give the best balance of speed and cost.

How do I get a ChatGPT API key?

Register for a free account, open your dashboard, and click “Generate key”. Your ChatGPT API key works immediately — set it as your API key and point the base URL at our endpoint. No approval queue and no waiting.

Which base URL do I use?

Set the base URL in your SDK or tool to https://api.chatgpt-api.dev/v1.

Ready to start building?

Get your API key and send your first request in under a minute.

Get startedDocs