- Image generation
- NEW · Oct 9
GPT Image 2 on QuickSilver Pro
GPT Image 2 through one OpenAI-compatible API. Supported features: text input and image output.
- Image output
You pay · per generated image
$0.01
OpenAI list source: openai.com
At a glance
- Modality
- Image generation
- Price / image
- $0.01
- Endpoint
- /v1/images/generations
- OpenAI-compatible
- Yes
- Latency · live
- —
GPT Image 2 generation at fixed standard quality and approximately 1.5 megapixels.
Try it
Runs on your own API key and balance, billed exactly like an API call.
Your image appears here.
The same request as code
curl https://api.quicksilverpro.io/v1/images/generations \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2",
"prompt": "A ripe red apple on a white marble table, soft studio light, product photo",
"size": "1024x1024",
"n": 1
}'import base64, os
from openai import OpenAI
client = OpenAI(base_url="https://api.quicksilverpro.io/v1", api_key=os.environ["QSP_KEY"])
result = client.images.generate(
model="gpt-image-2",
prompt="A ripe red apple on a white marble table, soft studio light, product photo",
size="1024x1024",
n=1,
)
with open("out.png", "wb") as f:
f.write(base64.b64decode(result.data[0].b64_json))import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.quicksilverpro.io/v1", apiKey: process.env.QSP_KEY });
const result = await client.images.generate({
model: "gpt-image-2",
prompt: "A ripe red apple on a white marble table, soft studio light, product photo",
size: "1024x1024",
n: 1,
});
fs.writeFileSync("out.png", Buffer.from(result.data[0].b64_json, "base64"));OpenAI Images API. The response is OpenAI-shaped — data[0].b64_json holds the image. One key for chat and images.
When is GPT Image 2 the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
Use GPT Image 2 when your application needs these capabilities: text input and image output.
- Text-to-image at a flat $0.01 per image
- Existing OpenAI Images API code, after a base URL swap
- One key and balance for chat and images
When to use something else
Choose a different model if your workflow requires capabilities beyond those listed here. Test your workload before committing to a model.
- Price per image matters mostFLUX.1 Schnell costs $0.003 per image.FLUX.1 Schnell $0.003 / img
- You want another OpenAI image modelGPT Image 2.5 Flare costs $0.018 per image.GPT Image 2.5 Flare $0.018 / img
- You want another OpenAI image modelGPT Image 2.5 Sunburst costs $0.018 per image.GPT Image 2.5 Sunburst $0.018 / img
Gateway behavior
Compatibility notes for this model.
size- 1024 × 1024 for now — more sizes are coming.
response- The image comes back as base64 in data[0].b64_json.
- /v1/images/generations: Supported
Where the price comes from
- Provider reference
- No provider list price is compared for this model.openai.com
- Catalog verified
Billed per generated image: $0.01.
/pricing.jsonFAQ
Common questions
A flat $0.01 per generated image. Output is fixed at approximately 1.5 megapixels and standard quality.
APIs: Images Generations. Capabilities: text input and image output. Use model="gpt-image-2" with base_url=https://api.quicksilverpro.io/v1. Use POST /v1/images/generations or the OpenAI SDK images.generate with model="gpt-image-2" and a prompt. The response includes the image in data[0].b64_json.