First & only jailbreak · Instant after payPlans
unlimitedcodex
Pricing

GPT-5.5 setup in 3 clear steps

Choose your package. Copy the right config. Start using GPT-5.5.

Select the package you purchased. The model, setup download, and ready-to-copy config will switch automatically.

About 5 minutes · No advanced setup knowledge needed

  1. 1Choose package
  2. 2Choose computer
  3. 3Set up GPT-5.5

Step 1

Which package did you buy?

Choose the same package shown in your order. Everything below will be prepared for it.

Your selectionGPT-5.5 XHigh · gpt-5.5 · config.toml is ready

Step 2

Which computer are you using?

We will show the right file and folder path for your computer.

Easiest method

Download the prepared setup file

The file already knows your selected model. It backs up existing files and asks only for your unlimitedcodex API key.

  1. 1Download the file
  2. 2Run it and paste your API key
  3. 3Start using GPT-5.5
Download Windows setupI prefer manual setup

Want an AI assistant to do it?

Download the package-specific TXT and give it to a trusted local/private AI assistant.

Download AI setup instructions

Manual option

Your ready-to-copy GPT-5.5 configuration

No model placeholder and no extra choice. The selected package sets the exact GPT-5.5 or GPT-5.6 Sol model; reasoning effort stays at xhigh.

Ready configuration

Modelgpt-5.5
Effortxhigh
File location%USERPROFILE%\.codex\config.toml
model_provider = "OpenAI"
model = "gpt-5.5"
review_model = "gpt-5.5"
model_reasoning_effort = "xhigh"
disable_response_storage = true
network_access = "enabled"

[model_providers.OpenAI]
name = "OpenAI"
base_url = "https://claude.kadirr.dev"
wire_api = "responses"
requires_openai_auth = true

[features]
goals = true

[sandbox_workspace_write]
network_access = true

Add your API key to auth.json

Replace the placeholder with the key from your delivery email. Never share the full key.

File location%USERPROFILE%\.codex\auth.json

Keep auth.json private. Do not commit it to a repository or send it in a support message.

{
  "auth_mode": "apikey",
  "OPENAI_API_KEY": "YOUR_UNLIMITEDCODEX_API_KEY"
}

Step 3

You are ready.

After saving both files, restart the application so the new GPT-5.5 provider is loaded.

Save both files

Save config.toml and auth.json in the .codex folder shown above.

Restart the app

Fully close and reopen Codex CLI, IDE, or the app.

Send one small prompt

Try a short request before starting a long repository task.

Optional API test

This request uses the same exact GPT-5.5 or GPT-5.6 Sol model selected above.

curl -X POST https://claude.kadirr.dev/v1/responses \
  -H "Authorization: Bearer YOUR_UNLIMITEDCODEX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "input": "Hello from unlimitedcodex",
    "stream": false
  }'

If something does not work

Most setup issues are fixed by one of these three checks.

401 or invalid_api_key

Open auth.json and check that OPENAI_API_KEY contains the complete delivered key.

404 or route not found

In config.toml, keep base_url as the provided base URL without /v1.

App still uses the old settings

Fully quit every process and reopen the application.

Still stuck? We will help.

Use the contact form and include your operating system and the error text. Never send your full API key.

Open contact form