LLM Reference
OpenAI API

Using GPT Image 2.5 Flare on OpenAI API

Implementation guide · GPT Image · OpenAI

Serverless

OpenAI API exposes GPT Image 2.5 Flare through model ID gpt-image-2.5-flare. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-09-09. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at OpenAI API and generate an API key.
  2. 2
    Use the OpenAI API SDK or REST API to call gpt-image-2.5-flare — see the documentation for request format.

Code Examples

Install
pip install openai
API key
OPENAI_API_KEY
Model ID
gpt-image-2.5-flare

Use the model slug directly, e.g. "gpt-4o" or "gpt-4.1-mini".

import os
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY from env
response = client.chat.completions.create(
    model="gpt-image-2.5-flare",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on OpenAI API

Capabilities

VisionMultimodalReasoningPrompt Caching

About GPT Image 2.5 Flare

GPT Image 2.5 Flare is OpenAI's fastest GPT Image 2.5 model for high-quality everyday image generation, released September 8, 2026. It accepts text and image inputs and produces image outputs, with low through max quality settings. Available via the Image API (model ids gpt-image-2.5-flare and dated snapshot gpt-image-2.5-flare-2026-09-08) and as the Responses API image generation tool model. OpenAI API multimodal token pricing: text input $5.00 / cached $1.25, image input $8.00 / cached $2.00, image output $30.00 per 1M tokens.

Model Specs

Released2026-09-08
ArchitectureAutoregressive Image

Provider

OpenAI API
OpenAI API

OpenAI

San Francisco, California, United States