Skip to content
OpenKey

GPT-5.5

OpenAIReleased Apr 24, 2026

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...

Try in playground
Context window
1.1M tokens
Max output
128K tokens
Input
file, image, text
Output
text
Tokenizer
GPT
Knowledge cutoff
Dec 1, 2025
Released
Apr 24, 2026
Reasoning
optional

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$5.00$0.150$5.15
Output$30.00$0.900$30.90
Cache read$0.500$0.015$0.515

Benchmarks

Artificial Analysis

Intelligence index
54.8
Coding index
74.9
Agentic index
44.9

Design Arena

CategoryEloWin rateRank
agenticgamedevagents121153.2%#5
agentichtmlslidesagents108434.2%#9
agenticslidesagents115043.5%#7
agenticslides(html)agents107733.2%#9
agenticslides(python-pptx)agents115545.2%#7
androidnativeagents126355.6%#4
Full-stackagents115444.6%#15
godotgamedevagents121753.2%#9
htmlslidesagents108234.1%#11
Mobile appsagents122751.5%#8
pptxslidesagents115745.3%#7
python-pptxslidesagents115243.3%#8
Web appsagents118145.4%#18
3Dmodels126453.4%#28
ASCII artmodels131663.3%#2
Codemodels129656.8%#15
Data vizmodels130458.8%#8
Game devmodels134862.7%#3
SVGmodels128460%#6
UI componentsmodels130157.6%#13
Websitesmodels128955.9%#19

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

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • response_format
  • seed
  • structured_outputs
  • tool_choice
  • tools

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model openai/gpt-5.5.

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-5.5",
    "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-5.5",
    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-5.5",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does GPT-5.5 cost via API?
Through OpenKey, GPT-5.5 costs $5.15 per 1M input tokens and $30.90 per 1M output tokens. That is the provider price ($5.00 / $30.00) plus a flat 3% fee — nothing else.
What is GPT-5.5's context window?
GPT-5.5 accepts up to 1.1M tokens of context and returns up to 128K tokens per request.
Is GPT-5.5 OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "openai/gpt-5.5" using any OpenAI SDK — only the base URL and API key change.
What inputs does GPT-5.5 support?
GPT-5.5 accepts file, image, text input and produces text output. Its knowledge cutoff is Dec 1, 2025.

More from OpenAI

All OpenAI models →