README.md

---
title: ChatMock
emoji: 🤖
colorFrom: blue
colorTo: indigo
sdk: docker
pinned: false
---
<div align="center">

# ChatMock

**Allows Codex to work in your favourite chat apps and coding tools.**

[![PyPI](https://img.shields.io/pypi/v/chatmock?color=blue&label=pypi)](https://pypi.org/project/chatmock/)
[![Python](https://img.shields.io/pypi/pyversions/chatmock)](https://pypi.org/project/chatmock/)
[![License](https://img.shields.io/github/license/RayBytes/ChatMock)](LICENSE)
[![Stars](https://img.shields.io/github/stars/RayBytes/ChatMock?style=flat)](https://github.com/RayBytes/ChatMock/stargazers)
[![Last Commit](https://img.shields.io/github/last-commit/RayBytes/ChatMock)](https://github.com/RayBytes/ChatMock/commits/main)
[![Issues](https://img.shields.io/github/issues/RayBytes/ChatMock)](https://github.com/RayBytes/ChatMock/issues)

<br>


</div>

<br>

## Install

#### Homebrew
```bash
brew tap RayBytes/chatmock
brew install chatmock
```

#### pipx / pip
```bash
pipx install chatmock
```

#### GUI
Download from [releases](https://github.com/RayBytes/ChatMock/releases) (macOS & Windows)

#### Docker
See [DOCKER.md](DOCKER.md)

#### Hugging Face
See [Hugging Face Deployment](#hugging-face-deployment)

<br>

## Getting Started

```bash
# 1. Sign in with your ChatGPT account
chatmock login

# 2. Start the server
chatmock serve
```

The server runs at `http://127.0.0.1:8000` by default. Use `http://127.0.0.1:8000/v1` as your base URL for OpenAI-compatible apps.

<br>

## Usage

<details open>
<summary><b>Python</b></summary>

```python
from openai import OpenAI

client = OpenAI(
    base_url="http://127.0.0.1:8000/v1",
    api_key="anything"  # not checked
)

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "hello"}]
)
print(response.choices[0].message.content)
```

</details>

<details>
<summary><b>cURL</b></summary>

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

</details>

<details>
<summary><b>Custom API (Plain Text)</b></summary>

```bash
# Request format: {"prompt": "..."}
# Response format: {"status": "success", "text": "..."}

curl http://127.0.0.1:8000/api \
  -H "Content-Type: application/json" \
  -d '{"prompt": "hello"}'

# You can also specify the model in the URL
curl http://127.0.0.1:8000/gpt-5.5/api \
  -H "Content-Type: application/json" \
  -d '{"prompt": "hello"}'
```

</details>

<br>

## Supported Models

- `gpt-5.5`
- `gpt-5.4`
- `gpt-5.4-mini`
- `gpt-5.2`
- `gpt-5.1`
- `gpt-5`
- `gpt-5.3-codex`
- `gpt-5.3-codex-spark`
- `gpt-5.2-codex`
- `gpt-5-codex`
- `gpt-5.1-codex`
- `gpt-5.1-codex-max`
- `gpt-5.1-codex-mini`
- `codex-mini`

<br>

## Features

- Tool / function calling
- Vision / image input
- Thinking summaries (via think tags)
- Configurable thinking effort
- Fast mode for supported models
- Web search tool
- OpenAI-compatible `/v1/responses` (HTTP + WebSocket)
- Ollama-compatible endpoints
- Reasoning effort exposed as separate models (optional)

<br>

## Configuration

All flags go after `chatmock serve`. These can also be set as environment variables.

| Flag | Env var | Options | Default | Description |
|------|---------|---------|---------|-------------|
| `--reasoning-effort` | `CHATGPT_LOCAL_REASONING_EFFORT` | none, minimal, low, medium, high, xhigh | medium | How hard the model thinks |
| `--reasoning-summary` | `CHATGPT_LOCAL_REASONING_SUMMARY` | auto, concise, detailed, none | auto | Thinking summary verbosity |
| `--reasoning-compat` | `CHATGPT_LOCAL_REASONING_COMPAT` | legacy, o3, think-tags | think-tags | How reasoning is returned to the client |
| `--fast-mode` | `CHATGPT_LOCAL_FAST_MODE` | true/false | false | Priority processing for supported models |
| `--enable-web-search` | `CHATGPT_LOCAL_ENABLE_WEB_SEARCH` | true/false | false | Allow the model to search the web |
| `--expose-reasoning-models` | `CHATGPT_LOCAL_EXPOSE_REASONING_MODELS` | true/false | false | List each reasoning level as its own model |

<details>
<summary><b>Web search in a request</b></summary>

```json
{
  "model": "gpt-5.4",
  "messages": [{"role": "user", "content": "latest news on ..."}],
  "responses_tools": [{"type": "web_search"}],
  "responses_tool_choice": "auto"
}
```

</details>

<details>
<summary><b>Fast mode in a request</b></summary>

```json
{
  "model": "gpt-5.4",
  "input": "summarize this",
  "fast_mode": true
}
```

</details>

<br>

## Notes

Use responsibly and at your own risk. This project is not affiliated with OpenAI.

<br>

## Hugging Face Deployment

1. **Get Auth**: Run `python chatmock.py info --json` locally and copy the output.
2. **Create Space**: Create a new **Docker** Space on Hugging Face.
3. **Upload**: Upload all project files to the Space.
4. **Secret**: In Space Settings, add a secret named `AUTH_JSON` and paste your auth data as the value.
5. **Done**: Your API will be available at `https://<user>-<space>.hf.space/api`

### Updating / Refreshing Session

If your API starts returning "Not signed in" errors, your session has likely expired. To fix it:
1. Run `chatmock login` on your local computer.
2. Run `python chatmock.py info --json` and copy the new output.
3. Go to your Space **Settings** -> **Variables and secrets**.
4. Edit the `AUTH_JSON` secret and paste the new value.
5. Save and the Space will automatically restart with the fresh session.

<br>

## Star History

[![Star History Chart](https://api.star-history.com/svg?repos=RayBytes/ChatMock&type=Timeline)](https://www.star-history.com/#RayBytes/ChatMock&Timeline)


python chatmock.py info --json


copy whole output of the command and paste it in the secret 

{
  "auth_mode": "chatgpt",
  "OPENAI_API_KEY": null,
  "tokens": {
    "id_token": "eyJhbGciOiJSUzI1NiIsImtpZCI6ImIxZGQzZjhmLTlhYWQtNDdmZS1iMGU3LWVkYjAwOTc3N2Q2YiIsInR5cCI6IkpXVCJ9.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.XipII74SWIUFNjC5XtqbL4d-usrKv0K2dSnPBt6Z5U6gGQExxPN50MfbyJymupd6IQP5eFjIF5An8O8JFNeJlKqg5dDHAZzkej1lyPTerYpGsbLhG1_nPk1As_TJ9U4yO24GBturjwcPaSgWQSMouv9YD7m7mbQ6lWFkuoKxNGA0NUKSAwp65awccKYndKnZ9iObOA7McGHOPwAXvDDPaoJRK67cNDSE8WSCFyW5ZqyzrJ3WbsaG-0k2vrVl0k5zka3kL1xxljqNdIUrensBZYYhUEy_zYvsbHczkSNzpYn3mCFlkNts1zp5EvWZXt4yStNeHhJwjNYkJylJQnG6u1O2tzgGfU-Di_DH1XY8S1M8DGuci92SQ2u3Kp8njRLy2ywD2yvz59hJhheWbaAwPWR9EhxizA-upEfyO65mQSaETSBaFRcL8d5hI6soaDHoeCxSsJYdzvsH8jwzxWI0vOp1r2_1u2BsDlLOTJ-NzheB4FqnQqzs4QmTSR_7wF4u3XI34DHqTEKzvrpAcAk4YGKRrWAEIzYmHSwMvUe_Rmw8OcBJkQpPvqLlODMAdPVGJ3lBz2FvrIWCor0-LUIK3A8LBqBYhmBdbyrZRedNS3V2W6M_T4Vk1QrEquLqqFa_lU7BMtYIL3w6v7oBxUozE_Ey3ndMw_Nop_gLBKxkgI8",
    "access_token": "eyJhbGciOiJSUzI1NiIsImtpZCI6IjE5MzQ0ZTY1LWJiYzktNDRkMS1hOWQwLWY5NTdiMDc5YmQwZSIsInR5cCI6IkpXVCJ9.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.15hsGF4sq4nJkOCmydaPjkHU6wwd_6gqi-E6yonICyktZ68-KWbSW5S5hGY6OHcQ51d8XdqfsE-O2g734oZDyla9tvmkVMLfHcNeEIfnjy0HwbmoqjbJvnJuvOTbRvWEffbGsOZW42PdhhCDHvHFpM0JAU9ll89nOIpPOEL8Cr9wosHaMJu4TVIvuQmrrKdNxOBCo2S9d8wNEcWMMg-4sKLSi9VJ2Rqq1ZqRqUDg33WFQ1ycWpqtgVcaNqtKGfIE2xh_83J-_5AuLAV8w2SEvq3x4DKaBk_yqnPYEF9XflzTz0QIlDihdnS0papYo_GkU2PumxCnWN_4nEwmd52KKgzIOkdsI5xfQpiyZKrudjnJasxmu0s1yb48jYpWUmWA3wLgmjmnERdE460rEvmVKaO_WkhfqomnNUEHSlRyXX4qzqQFxyq_sDaVBXZJY5a1ncqspXUi_VmXfAwz7KtSyMSeKmSaRIPp-c1Jy9Zut9C4D3nOwVuRtNlThghdeeFV9zWAVDwcSFCik-3fEbEEZ8uclYa-sCy5agwxsFFCHJbrTv2ZCvUOeSR8jlKI0UIugFsrTTxQ9WK8d2jjXy6AorCnlxxjtlTMzZcWOMwvNiSGtjF2D7HChWu6kKb2zHgXZRdWD0zXJnoV3sM2Hnx8SbAaPyheob35hP6p4wcHYNw",
    "refresh_token": "rt_LHMo6b6cqiSsJkwbp5LLnZoFOYmv-ZN3Kb0nTuRey9Q.arZgKwXuOopbbFXeQUVBhiLcNkYRP_e5ilkRit9bzaY",
    "account_id": "a1f2db17-f2c4-46bd-a934-07b213f5424f"
  },
  "last_refresh": "2026-05-01T04:16:26.900951Z"
}