GPT Image 2

proprietary

Max size

1536x1024

Input → output

text → image

Weights

Proprietary

Providers

1 provider · price, latency and uptime

ProviderPer imageLatency p50Uptime · hourly, 24hRetention

OpenAI

direct API

≤ $0.25–

–

may retain

Listed price: $5 / $30 per 1M
Most per image: 8,232 tokens · $0.25
Precision: –
Regions: default
Headquarters: –
Data retention: May retain prompts

Supported parameters

nsizequalitybackgroundmoderationoutput_formatoutput_compression

Uptime · last 3 days10-05 04:00 – 10-08 03:33 UTC

MonTueWedNow

By default the router tries our listings in routing order and fails over before the first byte — never mid-answer. Uptime is our own measurement; an hour stays grey until it has a sample. Open the row for the provider's specs and policies.

Quickstart

any SDK — only the base URL changes

curl https://api.routerplus.com/v1/images/generations \
  -H "Authorization: Bearer $TM_API_KEY" -H "content-type: application/json" \
  -d '{"model":"gpt-image-2","prompt":"a red dot","size":"1024x1024","quality":"low"}'

# OpenAI SDK — only the base URL changes
import base64, os
from openai import OpenAI
client = OpenAI(base_url="https://api.routerplus.com/v1", api_key=os.environ["TM_API_KEY"])
r = client.images.generate(model="gpt-image-2", prompt="a red dot",
  size="1024x1024", quality="low")
png = base64.b64decode(r.data[0].b64_json)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.routerplus.com/v1", apiKey: process.env.TM_API_KEY });
const r = await client.images.generate({ model: "gpt-image-2", prompt: "a red dot", size: "1024x1024", quality: "low" });
const png = Buffer.from(r.data[0].b64_json, "base64");

.qs pre[hidden] { display: block; border-top: 1px solid var(--code-line); } .qsb { display: none; } .qcode::before { content: attr(data-lang); display: block; color: var(--code-muted); font-size: 11px; margin-bottom: 6px; }

Pricing

prompt = text input, completion = image output, per 1M tokens

prompt	$5
completion	$30
per image, at most	8,232 tokens · $0.25

Every billed response carries usage.cost — recompute your bill from the wire.

Parameters

n — integer 1–4 (default 1)

size — auto · 1024x1024 · 1536x1024 · 1024x1536 (default auto)

quality — auto · low · medium · high (default auto)

background — auto · transparent · opaque (default auto)

moderation — auto · low (default auto)

output_format — png · jpeg · webp (default png)

output_compression — integer 0–100

Values outside these are refused with a 400 that names the field.

Uptime

10-05 04:00 – 10-08 03:33 UTC

Last 3 days–last 24h · TTFB p50 – · uptime n<100

MonTueWedNow

An hour counts at the best provider's uptime: a request goes to another provider when one fails. Grey hours have no sample yet.