IMAGE API

GPT Image 2.6 Flare · API guide

Use Flare to iterate on illustrations and product visuals. API guide · NewRouters Images API

POST/v1/tasksMODELgpt-image-2.6-flare

Official reference gpt-image-2.6-flareChecked 2026-11-05Official docs

Code examples & responses

Request & responseExamples

POST/v1/tasks

Server-side request

curl "https://newrouters.com/v1/tasks" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "gpt-image-2.6-flare",
  "input": {
    "prompt": "A blue ball bounces against a white background in a smooth loop.",
    "size": "auto",
    "quality": "low",
    "output_format": "gif"
  }
}'

Server-side request

const apiBaseUrl = "https://newrouters.com";
const apiKey = process.env.API_KEY;
if (!apiKey) throw new Error("Set API_KEY in your server environment");

const response = await fetch(apiBaseUrl + "/v1/tasks", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "Bearer " + apiKey
  },
  body: JSON.stringify({
  "model": "gpt-image-2.6-flare",
  "input": {
    "prompt": "A blue ball bounces against a white background in a smooth loop.",
    "size": "auto",
    "quality": "low",
    "output_format": "gif",
    "resolution": "2k"
  }
})
});

const result = await response.json();
if (!response.ok) throw new Error(JSON.stringify(result));
console.log(result);

Server-side request

import json
import os
from urllib.request import Request, urlopen

api_base_url = "https://newrouters.com"
api_key = os.environ["API_KEY"]
body = json.loads("{\"model\":\"gpt-image-2.6-flare\",\"input\":{\"prompt\":\"A blue ball bounces against a white background in a smooth loop.\",\"size\":\"auto\",\"quality\":\"low\",\"output_format\":\"gif\",\"resolution\":\"2k\"}}")

request = Request(
    api_base_url + "/v1/tasks",
    data=json.dumps(body).encode("utf-8"),
    headers={
    "Content-Type": "application/json",
    "Authorization": "Bearer " + api_key
    },
    method="POST",
)
with urlopen(request) as response:
    print(json.load(response))

The API origin is filled in. Set API_KEY before running. Examples never submit automatically.

ResponseSelected fields · illustrative values

202Task accepted

JSON

{
  "id": "TASK_ID",
  "status": "pending",
  "model": "gpt-image-2.6-flare",
  "result": null,
  "error": null
}

200Successful result

JSON

{
  "id": "TASK_ID",
  "status": "succeeded",
  "model": "gpt-image-2.6-flare",
  "result": {
    "assets": [
      "https://example.com/output.png"
    ]
  },
  "error": null
}

Retrieve results after submission

Request lifecycleAsynchronous media

Create a task01
POST /v1/tasks
Submit model + input. Save the returned task id.
202 · pending
Poll status02
GET /v1/tasks/{id}
Wait and poll again while pending or processing.
Wait → poll again
Read the outcome03
result.assets[] / error
Read the result for the terminal task state.
succeeded→ assetsfailed→ error

Use Flare to iterate on illustrations and product visuals. Use the NewRouters model ID gpt-image-2.6-flare.

Text to image · Reference image edits

Generations support JPEG, PNG, WebP and animated GIF. Use automatic sizing for GIF generation. The live sample returned nine frames at 200 ms per frame. Custom timing and frame counts are unverified.

curl "https://newrouters.com/v1/tasks" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "gpt-image-2.6-flare",
  "input": {
    "prompt": "A blue ball bounces against a white background in a smooth loop.",
    "size": "auto",
    "quality": "low",
    "output_format": "gif"
  }
}'

Save the task ID and poll GET /v1/tasks/{id} with the same key. On success, download the file from result.assets.

Token pricing

The default rate and price group 24 charge for actual usage at 60% of OpenAI standard pricing. Other groups use their account price card.

Per million tokens	OpenAI (USD)	NewRouters (credits)
Text input	5	300
Cached text input	1.25	75
Image input	8	480
Cached image input	2	120
Image output	30	1800

Model page, sample output and playground

For SVG generation, set output_format: "svg". The selected image model renders a reference and gpt-6-luna authors the vector file. Your account price card for the selected image model applies. Default pricing and group 24 charge 60% of standard rates for the image model’s reported usage. SVG authoring has no additional customer charge.

OpenAI · GPT Image 2.6 Flare · OpenAI Images API