chatmock 1.36

No project description provided

ChatMock

OpenAI & Ollama compatible API powered by your ChatGPT plan.

Use your ChatGPT Plus/Pro account to call OpenAI models from code or alternate chat UIs.

What It Does

ChatMock runs a local server that creates an OpenAI/Ollama compatible API, and requests are then fulfilled using your authenticated ChatGPT login with the oauth client of Codex, OpenAI's coding CLI tool. This allows you to use GPT-5, GPT-5-Codex, and other models right through your OpenAI account, without requiring an api key. You are then able to use it in other chat apps or other coding tools.
This does require a paid ChatGPT account.

Quickstart

Homebrew

brew tap RayBytes/chatmock
brew install chatmock

CLI

pipx install chatmock

GUI

If you're on macOS or Windows, you can download the GUI app from the GitHub releases.

Python

If you wish to just simply run this as a python flask server, you are also freely welcome too.

Clone or download this repository, then cd into the project directory. Then follow the instrunctions listed below.

1. Sign in with your ChatGPT account and follow the prompts

python chatmock.py login

You can make sure this worked by running python chatmock.py info

2. After the login completes successfully, you can just simply start the local server

python chatmock.py serve

Then, you can simply use the address and port as the baseURL as you require (http://127.0.0.1:8000 by default)

Reminder: When setting a baseURL in other applications, make you sure you include /v1/ at the end of the URL if you're using this as a OpenAI compatible endpoint (e.g http://127.0.0.1:8000/v1)

Docker

Read the docker instrunctions here

Examples

Python

from openai import OpenAI

client = OpenAI(
    base_url="http://127.0.0.1:8000/v1",
    api_key="key"  # ignored
)

resp = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "hello world"}]
)

print(resp.choices[0].message.content)

curl

curl http://127.0.0.1:8000/v1/chat/completions \
  -H "Authorization: Bearer key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{"role":"user","content":"hello world"}]
  }'

What's supported

• Tool/Function calling
• Vision/Image understanding
• Thinking summaries (through thinking tags)
• Thinking effort

Notes & Limits

• Requires an active, paid ChatGPT account.
• Some context length might be taken up by internal instructions (but they dont seem to degrade the model)
• Use responsibly and at your own risk. This project is not affiliated with OpenAI, and is a educational exercise.

Supported models

• gpt-5.4
• gpt-5.2
• gpt-5.1
• gpt-5
• gpt-5.3-codex
• gpt-5-codex
• gpt-5.2-codex
• gpt-5.1-codex
• gpt-5.1-codex-max
• gpt-5.1-codex-mini
• codex-mini

Customisation / Configuration

Thinking effort

• --reasoning-effort (choice of none,minimal,low,medium,high,xhigh)
  GPT-5 has a configurable amount of "effort" it can put into thinking, which may cause it to take more time for a response to return, but may overall give a smarter answer. Applying this parameter after serve forces the server to use this reasoning effort by default, unless overrided by the API request with a different effort set. The default reasoning effort without setting this parameter is medium.
  The gpt-5.1 family (including codex) supports low, medium, and high while gpt-5.1-codex-max adds xhigh. The gpt-5.2 and gpt-5.3 families (including codex) support low, medium, high, and xhigh. GPT-5.4 supports none, low, medium, high, and xhigh.

Thinking summaries

• --reasoning-summary (choice of auto,concise,detailed,none)
  Models like GPT-5 do not return raw thinking content, but instead return thinking summaries. These can also be customised by you.

OpenAI Tools

• --enable-web-search
  You can also access OpenAI tools through this project. Currently, only web search is available. You can enable it by starting the server with this parameter, which will allow OpenAI to determine when a request requires a web search, or you can use the following parameters during a request to the API to enable web search:
  
  responses_tools: supports [{"type":"web_search"}] / { "type": "web_search_preview" }
responses_tool_choice: "auto" or "none"

Example usage

{
  "model": "gpt-5.4",
  "messages": [{"role":"user","content":"Find current METAR rules"}],
  "stream": true,
  "responses_tools": [{"type": "web_search"}],
  "responses_tool_choice": "auto"
}

Expose reasoning models

• --expose-reasoning-models
  If your preferred app doesn’t support selecting reasoning effort, or you just want a simpler approach, this parameter exposes each reasoning level as a separate, queryable model. Each reasoning level also appears individually under ⁠/v1/models, so model pickers in your favorite chat apps will list all reasoning options as distinct models you can switch between.

Notes

If you wish to have the fastest responses, I'd recommend setting --reasoning-effort to low, and --reasoning-summary to none.
All parameters and choices can be seen by sending python chatmock.py serve --h
The context size of this route is also larger than what you get access to in the regular ChatGPT app.

When the model returns a thinking summary, the model will send back thinking tags to make it compatible with chat apps. If you don't like this behavior, you can instead set --reasoning-compat to legacy, and reasoning will be set in the reasoning tag instead of being returned in the actual response text.

Star History