# gpt-image-2

Canonical page: https://agentsky.dev/models/openai/gpt-image-2
JSON record: https://gateway.agentsky.dev/v1/endpoints/openai/gpt-image-2

gpt-image-2 is a image model from OpenAI, callable through the AgentSky API as openai/gpt-image-2 and billed per token (Single image generation (example): 1K (default): $0.0247 · 2K: $0.0297 · 4K: $0.033 · Other requests: Text input: $3.575 / 1M tokens · Text output: $0 / 1M tokens · Image output: $21.45 / 1M tokens).

Generate an image from a text prompt. The request may return RUNNING before the image is ready; poll GET /v1/runs/{runId} until COMPLETED. Returns one image. Configured flat-price generation supports square, landscape and portrait: 1K is 1024×1024, 1360×768 or 768×1360; 2K is 2048×2048, 2736×1536 or 1536×2736; 4K is 2880×2880, 3840×2160 or 2160×3840. Landscape and portrait use 16:9 and 9:16. Other routes support 1K only: low/high square and medium square, 3:2 or 2:3. Medium is the default.

After COMPLETED, decode run.output.data[0].b64_json from base64 to save the image.

## Facts

- **Id:** `openai/gpt-image-2`
- **Provider:** OpenAI
- **Kind:** image model
- **Billed per:** token
- **Timeout:** 9 min
- **Max request:** 1 MB
- **Character limit:** prompt up to 32,000

## Call it

`POST https://gateway.agentsky.dev/v1/run` with `{"provider": "openai", "endpoint": "gpt-image-2", "input": {…}}` and `Authorization: Bearer $AGENTSKY_API_KEY`.

### Input fields

| Field | Type | Required | Description |
|---|---|---|---|
| `prompt` | string | yes | What to draw, in plain language. Max: 32000. |
| `aspect_ratio` | string | no | Shape of the image: 1:1; flat-price routes also accept 16:9 or 9:16; native medium also accepts 3:2 or 2:3. Square when omitted. |
| `resolution` | string | no | Size class of the image: 1K; flat-price routes also accept 2K or 4K. 1K when omitted. |
| `quality` | string | no | Image quality. Consult pricing_routes for any configured flat-price generation; other requests use native token billing. Allowed: auto, low, medium, high. Default: "medium". |

## Example

### curl

```bash
# Set once per job; reuse this key and the identical body after a timeout.
: "${AGENTSKY_IDEMPOTENCY_KEY:?Set a unique, saved key for this job}"
curl --fail-with-body https://gateway.agentsky.dev/v1/run \
  -H "authorization: Bearer $AGENTSKY_API_KEY" \
  -H "content-type: application/json" \
  -H "Idempotency-Key: $AGENTSKY_IDEMPOTENCY_KEY" \
  -d '{"provider":"openai","endpoint":"gpt-image-2","input":{"prompt":"A paper airplane over a city at dusk, flat illustration"}}'
# If status is READY/RUNNING, poll GET /v1/runs/{runId} with the same API key.
```

### JavaScript

```js
// Node.js 20+. Save one unique key per job; reuse it with the identical body.
const key = process.env.AGENTSKY_IDEMPOTENCY_KEY;
if (!key || !process.env.AGENTSKY_API_KEY) {
  throw new Error("Set AGENTSKY_API_KEY and a saved AGENTSKY_IDEMPOTENCY_KEY first");
}
const base = "https://gateway.agentsky.dev";
const headers = {
  authorization: `Bearer ${process.env.AGENTSKY_API_KEY}`,
  "content-type": "application/json",
  "Idempotency-Key": key,
};
const body = JSON.stringify({
  "provider": "openai",
  "endpoint": "gpt-image-2",
  "input": {
    "prompt": "A paper airplane over a city at dusk, flat illustration"
  }
});
const sleep = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function request(path, options = {}) {
  for (let attempt = 0; attempt < 3; attempt++) {
    let response;
    let data;
    try {
      response = await fetch(base + path, {
        ...options, headers, signal: AbortSignal.timeout(180_000),
      });
      const text = await response.text();
      try { data = JSON.parse(text); } catch { /* Proxy timeouts may return HTML. */ }
    } catch (error) {
      if (attempt === 2) throw error; // Resume with the same key and body.
      await sleep(2000);
      continue;
    }
    // Failed runs can have non-2xx HTTP status. Never regenerate them automatically.
    if (data?.runId && data?.status) return data;
    if (response.ok && data) throw new Error("Unexpected response: missing runId/status");
    if (attempt < 2 && (response.status >= 500 || response.status === 408 || response.status === 429)) {
      await sleep(2000);
      continue; // POST retries keep the original key and body.
    }
    throw new Error(`HTTP ${response.status}: ${JSON.stringify(data ?? "Non-JSON response; retry with the same key and body")}`);
  }
}

let run = await request("/v1/run", { method: "POST", body });
console.log("Save runId:", run.runId);
const deadline = Date.now() + 30 * 60_000;
while (["READY", "RUNNING"].includes(run.status)) {
  if (Date.now() >= deadline) {
    throw new Error(`Still pending: poll /v1/runs/${run.runId} later; do not create a new job`);
  }
  await sleep(5000);
  run = await request(`/v1/runs/${encodeURIComponent(run.runId)}`);
}
console.log("Status:", run.status, "Charge:", run.price?.amount);
if (run.status !== "COMPLETED") {
  throw new Error(`Run ${run.runId}: ${JSON.stringify(run.error ?? run.status)}`);
}
console.log(run.output); // Output shape depends on the endpoint.
// READY/RUNNING price is provisional. Use the terminal receipt for reconciliation.
```

## Pricing

Single image generation (example): 1K (default): $0.0247 · 2K: $0.0297 · 4K: $0.033 · Other requests: Text input: $3.575 / 1M tokens · Text output: $0 / 1M tokens · Image output: $21.45 / 1M tokens

Read the final customer charge from price.amount.value after the run finishes. A RUNNING response is not the final bill.

## Questions

### What does gpt-image-2 do?

Generate an image from a text prompt. The request may return RUNNING before the image is ready; poll GET /v1/runs/{runId} until COMPLETED. Returns one image. Configured flat-price generation supports square, landscape and portrait: 1K is 1024×1024, 1360×768 or 768×1360; 2K is 2048×2048, 2736×1536 or 1536×2736; 4K is 2880×2880, 3840×2160 or 2160×3840. Landscape and portrait use 16:9 and 9:16. Other routes support 1K only: low/high square and medium square, 3:2 or 2:3. Medium is the default.

### How much does gpt-image-2 cost?

Single image generation (example): 1K (default): $0.0247 · 2K: $0.0297 · 4K: $0.033 · Other requests: Text input: $3.575 / 1M tokens · Text output: $0 / 1M tokens · Image output: $21.45 / 1M tokens, using your plan when signed in. The customer charge is returned as price.amount.value with its currency; READY/RUNNING values are provisional.

### What does gpt-image-2 take?

prompt is required; the rest of the fields are optional. Send them in the input object of a POST to /v1/run.

### What are the limits on gpt-image-2?

The catalog lists an execution timeout of 9 min. A request can return READY or RUNNING before completion; poll GET /v1/runs/{runId} with the same API key until it reaches a terminal status. An HTTP timeout does not prove the generation stopped.

### How do I retry safely and check the final charge?

Save a unique Idempotency-Key for each job. After a network error or HTML timeout, resend the identical POST body with the same key and API key to recover the existing run, then poll its runId. A new key can start another billable generation. An HTTP error or timeout does not establish the run outcome or final charge. Pending runs can still settle; check the terminal price.amount and billing state, and retain the runId for reconciliation. Do not automatically create a new job after a terminal failure.
