qcode-img gpt-image-2

完整文档（含详细 prompt 编写指南、Playground、与 OpenAI 官方 API 差异等）： docs.qcode.cc/docs/usage/image-2 →

Endpoint

Base URL: https://api.qcode.cc/qcode-img/v1

POST /v1/images/generations

curl https://api.qcode.cc/qcode-img/v1/images/generations \
  -H "Authorization: Bearer cr_YOUR_APIKEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A cyberpunk Tokyo street at night",
    "size": "1024x1024",
    "quality": "low",
    "n": 1
  }'

from openai import OpenAI
import base64

client = OpenAI(
    base_url="https://api.qcode.cc/qcode-img/v1",
    api_key="cr_YOUR_APIKEY",
    timeout=180.0,  # OpenAI SDK default is short, recommend 180s
)

result = client.images.generate(
    model="gpt-image-2",
    prompt="A cyberpunk Tokyo street at night",
    size="1024x1024",   # 1024x1024 / 1024x1536 / 1536x1024
    quality="low",      # low / medium / high
    n=1,
)
img_bytes = base64.b64decode(result.data[0].b64_json)
open("out.png", "wb").write(img_bytes)

const r = await fetch("https://api.qcode.cc/qcode-img/v1/images/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer cr_YOUR_APIKEY",
    "Content-Type":  "application/json",
  },
  body: JSON.stringify({
    model: "gpt-image-2",
    prompt: "A cyberpunk Tokyo street at night",
    size: "1024x1024",
    quality: "low",
    n: 1,
  }),
});
const json = await r.json();
const b64  = json.data[0].b64_json;

Parameters

Field	Type	Description	Default
model *	string		—
prompt *	string		—
size	string		1024x1024
quality	string		medium
n	integer		1

Response

{
  "created": 1777135432,
  "data": [
    {
      "b64_json": "iVBORw0KGgo...(base64 PNG)",
      "revised_prompt": "..."
    }
  ]
}

Image Editing Endpoint

POST /v1/images/edits  

curl https://api.qcode.cc/qcode-img/v1/images/edits \
  -H "Authorization: Bearer cr_YOUR_APIKEY" \
  -F "image=@cat.png" \
  -F "mask=@mask.png" \
  -F "prompt=put a tiny crown on the cat" \
  -F "size=1024x1024" \
  -F "quality=high" \
  -F "background=transparent" \
  -F "output_format=png" \
  -F "input_fidelity=high"

Error Codes

401 invalid_api_key
429 image_daily_limit
429 concurrency_exhausted
429 crs_daily_exhausted
503 image_provider_unavailable
413 image_too_large

Limits