RawFrame

GPT Image 2.5 Flare

OpenAI's GPT Image 2.5 Flare, the faster GPT Image 2.5 model for everyday text to image and editing.

  • Model id: openai/gpt-image-2.5-flare
  • Type: Image, from OpenAI
  • Modes: Text to image, Image edit
  • Prompt: up to 32,000 characters
  • Canceling: Only while queued. Generations finish within seconds once submitted.

Parameters

Set these in params. Anything left out takes the default, which is what the price estimate assumes.

ParameterAccepted valuesDefault
aspect_ratio1:1, 3:2, 2:3, 16:9, 9:16, 4:3, 3:4, 21:91:1
num_outputs1 to 101
output_formatpng, jpeg, webpprovider's

References

Pass media in references, each with a role and an upload_id or HTTPS url (Uploads). When mode is left out it is inferred from the roles.

RoleUsed asAt most
source_imageImage to edit1
reference_imageSubject or style reference15
maskEdit mask1

Pricing

Billed per image delivered. The full price list for your account is on the dashboard's billing page and in pricing from GET /v1/models/openai%2Fgpt-image-2.5-flare. Each request reserves its maximum price and is charged for what was produced (Pricing and credits).

Examples

Text to image

import { RawFrame } from "@rawframe/sdk";

const rf = new RawFrame();

const generation = await rf.generations.createAndWait({
  model: "openai/gpt-image-2.5-flare",
  prompt: "A ceramic coffee cup on a sunlit wooden table, soft shadows, product photo",
  params: { aspect_ratio: "1:1" },
});
console.log(generation.outputs?.[0]?.url);

Wide banner

import { RawFrame } from "@rawframe/sdk";

const rf = new RawFrame();

const generation = await rf.generations.createAndWait({
  model: "openai/gpt-image-2.5-flare",
  prompt: "A watercolor skyline of a coastal city at dawn, pastel colors, lots of empty sky",
  params: { aspect_ratio: "16:9" },
});
console.log(generation.outputs?.[0]?.url);

On this page