Skip to main content
NewSeedance 2.5 is live→
ModelRunner
openai avatar

GPT Image 2.5 Flare API

openai/gpt-image-2.5/flare/text-to-image

Generate images from a text prompt — precise multi-part instruction-following and legible in-image text across full-page layouts, at roughly half the latency of GPT Image 2.

0.0362
OpenAPI

Model Input

Input

The text prompt describing the image to generate. Put any wording you want rendered inside the image in quotes and say where it should appear.

The aspect ratio and framing of the generated image.

Additional Settings

Customize your input with more control.

Min: 1 - Max: 4

How many images to generate from this prompt. Each image is charged as its own generation.

The file format of the generated image.

You need to be logged in to run this model and view results.
Log in

Model Output

Output

Generated image output
Generated in 19.502 seconds
Logs (1 lines)

Model Example Requests

Examples

Example output 1Example output 2

GPT Image 2.5 Flare API

GPT Image 2.5 Flare is a text-to-image AI model by openai. On ModelRunner it runs through a REST API or via MCP from any AI assistant, at $0.0362 per image.

POST https://queue.modelrunner.run/openai/gpt-image-2.5/flare/text-to-image

cURL

# Submit a request to the queue. Input fields go at the top level of the
# body. The optional reserved "metadata" object holds your own flat string
# tags — stored on the request, never sent to the model; filter later with
# GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>.
curl -X POST https://queue.modelrunner.run/openai/gpt-image-2.5/flare/text-to-image \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Scene: a farmers-market artisan bakery stall poster pinned to a weathered wooden board. Subject: a rustic sourdough l…",
    "image_size": "landscape_4_3",
    "num_images": 1,
    "output_format": "png",
    "metadata": {
      "project": "my-project"
    }
  }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }

# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/openai/gpt-image-2.5/flare/text-to-image/requests/$REQUEST_ID/status" \
  -H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/openai/gpt-image-2.5/flare/text-to-image/requests/$REQUEST_ID" \
  -H "Authorization: Key $MRUN_API_KEY"

JavaScript

import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("openai/gpt-image-2.5/flare/text-to-image", {
  input: {
    "prompt": "Scene: a farmers-market artisan bakery stall poster pinned to a weathered wooden board. Subject: a rustic sourdough l…",
    "image_size": "landscape_4_3",
    "num_images": 1,
    "output_format": "png"
  },
});
console.log(result);

Python

import os
import requests

headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}

submitted = requests.post(
    "https://queue.modelrunner.run/openai/gpt-image-2.5/flare/text-to-image",
    headers=headers,
    json={
      "prompt": "Scene: a farmers-market artisan bakery stall poster pinned to a weathered wooden board. Subject: a rustic sourdough l…",
      "image_size": "landscape_4_3",
      "num_images": 1,
      "output_format": "png"
    },
).json()

# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()

Input parameters

Input parameters of GPT Image 2.5 Flare
NameTypeRequiredDescription
promptstringyesThe text prompt describing the image to generate. Put any wording you want rendered inside the image in quotes and say where it should appear.
image_sizeenumnoThe aspect ratio and framing of the generated image. One of: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9. Default: "landscape_4_3".
num_imagesintegernoHow many images to generate from this prompt. Each image is charged as its own generation. Default: 1.
output_formatenumnoThe file format of the generated image. One of: jpeg, png, webp. Default: "png".

Machine-readable: OpenAPI schema · llms.txt

Use GPT Image 2.5 Flare from Claude & Cursor (MCP)

Point Claude Code, Claude Desktop, Cursor, or any MCP client at the ModelRunner MCP server and GPT Image 2.5 Flare becomes a tool your assistant can call directly — it authorizes via OAuth (no API key in config) and runs this model with the run_model tool using the endpoint openai/gpt-image-2.5/flare/text-to-image.

MCP client config (Claude Desktop, Cursor)

{
  "mcpServers": {
    "modelrunner": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
    }
  }
}

Claude Code

claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcp

Then ask your assistant, for example: “Run openai/gpt-image-2.5/flare/text-to-image on ModelRunner to generate image”. MCP setup guide.

Model Details

Model Details

GPT Image 2.5 Flare turns a text prompt into a finished image. It is the everyday default tier of the GPT Image 2.5 line — higher quality than GPT Image 2 at roughly half the latency — and its standout strength is following complex, multi-part visual instructions exactly: counts, placement, style and medium stated together in one prompt all land. It also holds a whole page of structured information in a single pass, so posters, labels, slides and diagrams come out legible and in register, and scenes anchored to real-world facts render with accurate detail instead of a generic approximation.

## Best for - Posters, flyers and album covers where quoted wording must appear exactly as written - Product labels, packaging and signage mockups that need readable type - Infographics, slides and diagrams whose labels stay legible at normal viewing size - Scenes that specify counts, positions and style together in one prompt - High-volume or interactive image generation where turnaround matters as much as quality

## Choose another model when - You want to edit an existing picture or work from reference photos — this endpoint takes text only; use an image-editing model - The image will be viewed large or inspected close up — this tier is tuned for fast everyday generation, so pick a premium high-detail image model - Your subject falls outside OpenAI's content policy — filtering applies to every request and cannot be relaxed

## Tips - Write the prompt in labeled sections — scene, subject, details, constraints — rather than one run-on line; plain formatting beats special syntax - Put required wording in quotes and describe its position and typography; spell unusual words or brand names letter by letter - Ask for "photorealistic" or "real photograph" explicitly when that is the goal - For people, name body framing, relative scale, gaze and interaction with objects - Camera and lens details are cues for appearance, not exact optical simulation

## Limitations - Every request runs at the standard high-quality setting; the two extra-detail tiers GPT Image 2.5 adds are not selectable here - `image_size` offers six named presets only — no custom width and height - `num_images` returns up to four images in one call; each is charged as its own generation

To run via the ModelRunner JavaScript client: ```js import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("openai/gpt-image-2.5/flare/text-to-image", { input: { prompt: 'a vintage travel poster of Kyoto with the headline "VISIT JAPAN" across the top in bold serif capitals', image_size: "landscape_4_3", num_images: 1, output_format: "png", }, }); ```