OpenAI · Images
GPT Image 2.5 Flare API price
OpenAI’s GPT Image 2.5 Flare through one prepaid, OpenAI-compatible key: $0.006 per image, the provider’s list price with nothing added per request.
GPT Image 2.5 Flare price
- Price
- $0.006per image
- $5 per 1M prompt tokens + $30 per 1M image tokens
OpenAI’s list price, in US dollars. Tokens.Pay adds a 5% fee (minimum $0.79) when you add credit, never per request.
What GPT Image 2.5 Flare is good at
The second GPT Image 2.5 variant, for a different look from the same prompt.
In short: a different look from the same prompt.
Images model, called at /v1/images/generations. Listed under image generation.
GPT Image 2.5 Flare endpoint and id
- Provider
- OpenAI
- Type
- Images
- Endpoint
/v1/images/generations- Model id
gpt-image-2-5-flare
What GPT Image 2.5 Flare costs per request
The list price, multiplied out.
| Images | Cost |
|---|---|
| 1 | $0.006000 |
| 100 | $0.6000 |
| 1,000 | $6.00 |
At $0.006 per image ($5 per 1M prompt tokens + $30 per 1M image tokens), OpenAI’s list price.
GPT Image 2.5 Flare cost calculator
Set how much you need. The provider bills per unit; this is the arithmetic.
Call GPT Image 2.5 Flare with the OpenAI SDK
Base URL https://api.airuntime.dev/v1, your key as the bearer token, and model set to gpt-image-2-5-flare.
curl
curl https://api.airuntime.dev/v1/images/generations \
-H "Authorization: Bearer $TOKENS_PAY_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-image-2-5-flare",
"prompt": "A brass coin on a dark desk",
"size": "1024x1024"
}'
Python
from openai import OpenAI
import os
client = OpenAI(base_url="https://api.airuntime.dev/v1", api_key=os.environ["TOKENS_PAY_KEY"])
image = client.images.generate(model="gpt-image-2-5-flare", prompt="A brass coin on a dark desk", size="1024x1024")
print(image.data[0].url or "base64 image received")
Node
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airuntime.dev/v1", apiKey: process.env.TOKENS_PAY_KEY });
const image = await client.images.generate({ model: "gpt-image-2-5-flare", prompt: "A brass coin on a dark desk", size: "1024x1024" });
console.log(image.data[0].url ?? "base64 image received");
Who processes GPT Image 2.5 Flare requests
Your code calls AI Runtime directly. It forwards the request to the provider and keeps only the bill.
Processing and storage
- Model provider
- OpenAI · data terms
- Gateway
- AI Runtime, AWS us-east-1
Not stored by Tokens.Pay or AI Runtime. Prompts and outputs exist in memory only while the request runs; we keep the billing record. The provider processes the request under its own terms. Zero data retention, exactly
Compare GPT Image 2.5 Flare with similar models
| Model | Provider | Price |
|---|---|---|
| GPT Image 2.5 Flare (this page) | OpenAI | $0.006 per image |
| GPT Image 2.5 Sunburst | OpenAI | $0.006 per image |
GPT Image 2.5 Flare API questions
How much does the GPT Image 2.5 Flare API cost?
$0.006 per image, OpenAI’s list price. Tokens.Pay adds nothing per request; a 5% fee (minimum $0.79) applies when you add credit.
What is the model id for GPT Image 2.5 Flare?
Send model "gpt-image-2-5-flare" to https://api.airuntime.dev/v1/images/generations with your Tokens.Pay key as the bearer token. Any OpenAI-compatible SDK works.
Does Tokens.Pay store my GPT Image 2.5 Flare prompts?
No. AI Runtime, the gateway your key calls, keeps prompts and outputs in memory only while the request runs and stores just the billing record. The request is processed by OpenAI, under the provider’s own API data terms.
Add credit, then call GPT Image 2.5 Flare.
From $5, plus a 5% top-up fee (minimum $0.79). No subscription; paid credit never expires.
Add credit