questions/How-to

How do I use OpenAI GPT Image 2?

To use OpenAI GPT Image 2, install the OpenAI SDK (any language), point base_url at https://api.aigateway.sh/v1 with an sk-aig-... key, and set model="openai/gpt-image-2". That's it — no provider account, no separate billing. OpenAI's model is served through AIgateway's OpenAI-compatible endpoint so every existing OpenAI integration (Cursor, LangChain, Vercel AI SDK) works unchanged.

How it works

1. Grab an AIgateway key

Sign in at aigateway.sh with GitHub or Google, open the dashboard, and copy an sk-aig-... key. No credit card required to claim a key — the free tier is 100 requests/day on Kimi K2.6 so you can test end-to-end before you upgrade.

2. Point the OpenAI SDK at AIgateway

Every OpenAI client library ships with a base_url (Python) or baseURL (Node) field. Set it to https://api.aigateway.sh/v1 and drop in your sk-aig-... key. Nothing else in your application code needs to change — the request and response schemas are OpenAI-identical.

3. Set model="openai/gpt-image-2"

On your chat.completions.create call (or images, embeddings, audio — whichever endpoint matches the image modality), pass model="openai/gpt-image-2". AIgateway handles provider auth, billing, retries, and transformation so OpenAI-specific quirks don't leak into your code.

Code example

Python
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

img = client.images.generate(
    model="openai/gpt-image-2",
    prompt="A studio photo of a red ceramic mug on white marble",
    size="1024x1024",
)
print(img.data[0].url)
Node / TypeScript
// npm i aigateway-js openai
// aigateway-js: sub-accounts, evals, replays, jobs, webhook verify.
// openai SDK: chat/embeddings/images/audio — drop-in compat.
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.aigateway.sh/v1",
  apiKey: process.env.AIGATEWAY_KEY,
});

const img = await client.images.generate({
  model: "openai/gpt-image-2",
  prompt: "A studio photo of a red ceramic mug on white marble",
  size: "1024x1024",
});
console.log(img.data[0].url);

Related

FAQ

Do I need a OpenAI account to use OpenAI GPT Image 2?

No. AIgateway provides a unified sk-aig-... key that routes to OpenAI on your behalf. You only need an AIgateway account.

Does OpenAI GPT Image 2 support tool calling?

OpenAI GPT Image 2 does not support tool calling natively. Use it for generation; route tool-calling prompts to a model like Claude Sonnet 4.6 or GPT-5.4.

What is the context window of OpenAI GPT Image 2?

Context window details for OpenAI GPT Image 2 are on the spec page at /models/openai/gpt-image-2.

Is OpenAI GPT Image 2 free to try?

AIgateway's free tier gives 100 requests/day on Kimi K2.6. Other models (including OpenAI GPT Image 2 if it isn't Kimi K2.6) require a $5 top-up, then pass-through pricing.

Can I use OpenAI GPT Image 2 with Cursor or LangChain?

Yes — anything that speaks OpenAI's API shape works. Set base_url to https://api.aigateway.sh/v1, paste your AIgateway key, and set the model string. Cursor, Cline, Continue, LangChain, LlamaIndex, Vercel AI SDK all supported.

TRY IT NOW

One key, every model. Free tier, no card.

Get an AIgateway keyOpen the playground