# gpt-image-2/text-to-image

> OpenAI's GPT Image 2 Text-to-Image generates high-quality images from natural-language prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

- **Provider:** Openai
- **Category:** text-to-image
- **Price:** $0.0570 (~~$0.0600~~) per run

## Key Features

- Strong prompt fidelity — accurately renders complex multi-element scenes with precise spatial relationships.
- High-quality output — production-grade images with natural lighting, composition, and detail.
- Accurate text rendering — one of the best models for generating readable text within images.
- Flexible aspect ratios — supports 10 ratio options from 1:1 to 21:9 for any use case.
- Production-ready API — simple integration with quality/resolution tiers for cost optimization.
- Multiple resolution tiers: 1k, 2k, and 4k for preview through production workflows.

## Parameters

| Parameter | Required | Description |
| --- | --- | --- |
| `prompt` | Yes | Detailed description of the image to generate. |
| `aspect_ratio` | No | Ratio options: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. |
| `resolution` | No | Output resolution: '1k', '2k', or '4k' (default: '1k'). |
| `quality` | No | Quality level: 'low', 'medium' (default), or 'high'. |
| `output_format` | No | Output format: 'png', 'jpeg', or 'webp' (default: 'png'). |
| `enable_base64_output` | No | Return base64-encoded image data instead of URL. |
| `enable_sync_mode` | No | Enable synchronous response mode. |

## How to Use

1. Write a detailed prompt describing the image — GPT Image excels with natural language descriptions.
2. Choose aspect ratio from the 10 available options.
3. Select quality (low/medium/high) and resolution (1k/2k/4k) based on your needs.
4. Generate and review results — iterate on your prompt for improvements.

## Code Examples

### Python

```python
import os
import requests

response = requests.post(
    "https://aircube.ai/api/v3/gpt-image-2/text-to-image",
    headers={
        "Authorization": "Bearer " + os.environ["AIRCUBE_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
    "prompt": "A minimalist poster design with bold text reading 'DREAM BIG' in white sans-serif font on a gradient sunset background",
    "aspect_ratio": "9:16",
    "quality": "high",
    "resolution": "2k",
    "output_format": "png"
},
    timeout=300,
)
data = response.json()

if data["success"]:
    print("ID:", data["data"]["id"], "Status:", data["data"]["status"])
else:
    print("Error:", data["error"]["message"])
```

### Node.js

```javascript
const response = await fetch("https://aircube.ai/api/v3/gpt-image-2/text-to-image", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.AIRCUBE_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "prompt": "A minimalist poster design with bold text reading 'DREAM BIG' in white sans-serif font on a gradient sunset background",
  "aspect_ratio": "9:16",
  "quality": "high",
  "resolution": "2k",
  "output_format": "png"
}),
});

const data = await response.json();

if (data.success) {
  console.log("ID:", data.data.id, "Status:", data.data.status);
} else {
  console.error("Error:", data.error.message);
}
```

### cURL

```curl
curl -X POST "https://aircube.ai/api/v3/gpt-image-2/text-to-image" \
  -H "Authorization: Bearer $AIRCUBE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "prompt": "A minimalist poster design with bold text reading 'DREAM BIG' in white sans-serif font on a gradient sunset background",
  "aspect_ratio": "9:16",
  "quality": "high",
  "resolution": "2k",
  "output_format": "png"
}'
```

### Python (Async)

```python
import os
import time
import requests

# 1. Submit
response = requests.post(
    "https://aircube.ai/api/v3/gpt-image-2/text-to-image",
    headers={
        "Authorization": "Bearer " + os.environ["AIRCUBE_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
    "prompt": "A minimalist poster design with bold text reading 'DREAM BIG' in white sans-serif font on a gradient sunset background",
    "aspect_ratio": "9:16",
    "quality": "high",
    "resolution": "2k",
    "output_format": "png"
},
    timeout=300,
)
data = response.json()

if not data["success"]:
    print("Error:", data["error"]["message"])
    exit(1)

generation_id = data["data"]["id"]
print(f"Submitted: {generation_id}")

# 2. Poll until completed
while True:
    time.sleep(5)
    r = requests.get(
        f"https://aircube.ai/api/v3/status/{generation_id}",
        headers={"Authorization": "Bearer " + os.environ["AIRCUBE_API_KEY"]},
    )
    result = r.json()["data"]

    if result["status"] == "completed":
        print(result["output_url"])
        break
    elif result["status"] == "failed":
        print("Generation failed")
        break
```

### Node.js (Async)

```javascript
// 1. Submit
const response = await fetch("https://aircube.ai/api/v3/gpt-image-2/text-to-image", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.AIRCUBE_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "prompt": "A minimalist poster design with bold text reading 'DREAM BIG' in white sans-serif font on a gradient sunset background",
  "aspect_ratio": "9:16",
  "quality": "high",
  "resolution": "2k",
  "output_format": "png"
}),
});
const data = await response.json();

if (!data.success) {
  console.error("Error:", data.error.message);
  process.exit(1);
}

const generationId = data.data.id;
console.log("Submitted:", generationId);

// 2. Poll until completed
while (true) {
  await new Promise((r) => setTimeout(r, 5000));
  const res = await fetch(
    `https://aircube.ai/api/v3/status/${generationId}`,
    { headers: { "Authorization": "Bearer " + process.env.AIRCUBE_API_KEY } },
  );
  const result = (await res.json()).data;

  if (result.status === "completed") {
    console.log(result.output_url);
    break;
  } else if (result.status === "failed") {
    console.error("Generation failed");
    break;
  }
}
```

### cURL (Async)

```curl
# 1. Submit
RESPONSE=$(curl -s -X POST "https://aircube.ai/api/v3/gpt-image-2/text-to-image" \
  -H "Authorization: Bearer $AIRCUBE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "prompt": "A minimalist poster design with bold text reading 'DREAM BIG' in white sans-serif font on a gradient sunset background",
  "aspect_ratio": "9:16",
  "quality": "high",
  "resolution": "2k",
  "output_format": "png"
}')

ID=$(echo "$RESPONSE" | jq -r '.data.id')
echo "Submitted: $ID"

# 2. Poll until completed
while true; do
  sleep 5
  STATUS_RES=$(curl -s "https://aircube.ai/api/v3/status/$ID" \
    -H "Authorization: Bearer $AIRCUBE_API_KEY")
  STATUS=$(echo "$STATUS_RES" | jq -r '.data.status')

  if [ "$STATUS" = "completed" ]; then
    echo "$STATUS_RES" | jq -r '.data.output_url'
    break
  elif [ "$STATUS" = "failed" ]; then
    echo "Generation failed"; break
  fi
done
```

## Pricing

| Resolution | Duration | Cost |
| --- | --- | --- |
| 1k | low quality | $0.01 |
| 2k | low quality | $0.02 |
| 4k | low quality | $0.03 |
| 1k | medium quality | $0.06 |
| 2k | medium quality | $0.10 |
| 4k | medium quality | $0.18 |
| 1k | high quality | $0.22 |
| 2k | high quality | $0.40 |
| 4k | high quality | $0.72 |

### Billing Rules

- Pricing varies by quality x resolution combination.
- Low quality: $0.01 (1k), $0.02 (2k), $0.03 (4k).
- Medium quality: $0.06 (1k), $0.10 (2k), $0.18 (4k).
- High quality: $0.22 (1k), $0.40 (2k), $0.72 (4k).
- Failed generations are not charged.

## Best Use Cases

- Marketing creatives — generate hero images, banners, and ad assets with text overlays.
- E-commerce — product visualization and lifestyle imagery at scale.
- Landing pages — custom hero images and section graphics.
- Social media — platform-specific visuals with accurate text rendering.
- Concept art — rapid creative exploration with precise prompt control.
- Typography-driven visuals — designs requiring readable embedded text.

## Pro Tips

- GPT Image excels at text rendering — include specific text you want in the image within quotes.
- Use natural language descriptions rather than keyword lists for best results.
- Specify the artistic medium: 'oil painting', 'digital illustration', '3D render', 'photograph'.
- For text-heavy designs, describe text placement explicitly: 'centered bold title reading...'
- Use 'low' quality at '1k' for rapid iteration ($0.01), then 'high' at '4k' for final production.

## Notes

- 10 aspect ratio options available for flexible composition.
- Output formats: PNG, JPEG, or WebP.
- Content policy applies — certain subjects will be filtered.
- Median generation time: approximately 58 seconds.

## FAQ

**Q: What is the GPT Image 2 API?**

OpenAI's latest image generation model available through AirCube — known for exceptional prompt fidelity, text rendering capability, and flexible quality/resolution tiers.

**Q: Can GPT Image 2 render text in images?**

Yes — it's one of the best models for generating readable text within images. Include the desired text in quotes in your prompt.

**Q: What resolutions are available?**

Three tiers: 1k, 2k, and 4k, each available at low, medium, or high quality levels.

**Q: How does pricing work?**

Pricing is a grid of quality x resolution: from $0.01 (low/1k) to $0.72 (high/4k). Choose based on your use case.

**Q: What aspect ratios are supported?**

10 options: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9.

**Q: Can I use outputs commercially?**

Yes — generated images are yours to use commercially.