GPT Image 2

About

GPT Image 2 is OpenAI’s frontier image model, available through the same Sogni key as every native model. It is the strongest instruction-follower in the catalog, renders text nearly flawlessly, and accepts up to sixteen reference images.

As a partner model it runs on vendor infrastructure rather than Supernet GPU workers, is billed in Premium Spark only (no SOGNI fallback), and is priced by output-image tokens — quality and references move the price; see the table.

Pricing

On the Sogni API you pay per render in Spark (1 Spark = $0.005). Prefer a flat rate? The Sogni app runs GPT Image 2 and 100+ other models credit-free under fair use.

Premium Spark required — purchased credits; free Spark does not apply.

Pricing is token-based: reference images add input-token cost; later outputs in a batch reuse cached references.

API

One Sogni API key reaches every model on the Supernet — call GPT Image 2 by id.

import { SogniClient } from '@sogni-ai/sogni-client';

const client = await SogniClient.createInstance({
  appId: crypto.randomUUID(),
  apiKey: process.env.SOGNI_API_KEY,
  network: 'fast',
});

const project = await client.projects.create({
  type: 'image',
  modelId: 'gpt-image-2',
  positivePrompt: 'a slothicorn surfing a wave of liquid paint, studio lighting',
  numberOfMedia: 1,
});

const [url] = await project.waitForCompletion();
console.log(url); // result link — download within 24h

curl https://api.sogni.ai/v1/creative-agent/workflows \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SOGNI_API_KEY" \
  -d '{
    "input": {
      "title": "First render",
      "steps": [{
        "id": "step1",
        "toolName": "generate_image",
        "arguments": { "prompt": "a slothicorn surfing a wave of liquid paint, studio lighting", "model": "gpt-image-2" }
      }]
    },
    "confirm_cost": true
  }'

REST workflow alias: gpt-image-2. Pin the exact id with the SDK. Full reference at docs.sogni.ai.