Skip to content
OpenKey

GPT-5 Image

OpenAIReleased Oct 14, 2025

[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...

Try in playground
Context window
400K tokens
Max output
128K tokens
Input
image, text, file
Output
image, text
Tokenizer
GPT
Released
Oct 14, 2025
Reasoning
always on

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$10.00$0.300$10.30
Output$10.00$0.300$10.30
Cache read$1.25$0.037$1.29

Benchmarks

Design Arena

CategoryEloWin rateRank
graphicdesignmodels121251.9%#6
imagemodels121954.1%#7
logomodels122354.2%#6

Head-to-head preference voting. How we filter and rank

Supported parameters

  • frequency_penalty
  • include_reasoning
  • logit_bias
  • logprobs
  • max_tokens
  • presence_penalty
  • reasoning
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model openai/gpt-5-image.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5-image",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="openai/gpt-5-image",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "openai/gpt-5-image",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does GPT-5 Image cost via API?
Through OpenKey, GPT-5 Image costs $10.30 per 1M input tokens and $10.30 per 1M output tokens. That is the provider price ($10.00 / $10.00) plus a flat 3% fee — nothing else.
What is GPT-5 Image's context window?
GPT-5 Image accepts up to 400K tokens of context and returns up to 128K tokens per request.
Is GPT-5 Image OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "openai/gpt-5-image" using any OpenAI SDK — only the base URL and API key change.
What inputs does GPT-5 Image support?
GPT-5 Image accepts image, text, file input and produces image, text output.

More from OpenAI

All OpenAI models →