GPT-5 Image Mini is OpenAI's compact multimodal model, released 2025-10, that pairs GPT-5 Mini language capabilities with GPT Image 1 Mini for efficient image generation. It handles detailed image editing and text rendering with lower latency and cost than the full-size model, and suits applications needing both visual creation and text processing at scale.
MirAPI doesn’t offer this model. The prices shown are the official list prices.
Modalities
inFileinImageinTextoutImage
Price / 1M
$2.50 / $2.00
Context
400K
Released
Oct 16, 2025
Capabilities
ReasoningVisionLong contextPrompt cachingStructured output
Parameters
Request parameters this model accepts through the API.
include_reasoninglogprobsmax_tokensreasoningresponse_formatseedstructured_outputstemperaturetop_logprobstop_pverbosity
Quick start
POST /v1/images/generations/import os from openai import OpenAI client = OpenAI( base_url="https://api.mirapi.ai/v1", # changed api_key=os.environ["MIRAPI_API_KEY"], # changed ) img = client.images.generate( model="", prompt="A red bicycle leaning on a white wall", n=1, size="1024x1024", ) # img.data[0].b64_json — or .url, depending on the model
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.mirapi.ai/v1", // changed apiKey: process.env.MIRAPI_API_KEY, // changed }); const img = await client.images.generate({ model: "", prompt: "A red bicycle leaning on a white wall", n: 1, size: "1024x1024", });
curl https://api.mirapi.ai/v1/images/generations/ \ -H "Authorization: Bearer $MIRAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "", "prompt": "A red bicycle leaning on a white wall", "n": 1, "size": "1024x1024" }'
Links
Wire GPT-5 Image Mini into your product
Start free1M free tokens to start, no card required. It’s OpenAI-compatible, so you only change the base URL.