OpenAI & Ollama compatible API powered by your ChatGPT account.

This is a fork of RayBytes/chatmock. The original Flask + synchronous requests stack has been replaced with FastAPI + async httpx, a layered architecture (router / service / infra), pydantic-settings configuration, and uv as the build system.

Integration and coverage badges are updated from local runs. Refresh both by running scripts/test.sh with GIST_TOKEN available in your environment or .env.

gptmock runs a local server that proxies requests to the ChatGPT Codex backend, exposing an OpenAI/Ollama compatible API. Use GPT-5, GPT-5-Codex, and other models directly from your ChatGPT Plus/Pro subscription — no API key required.

Migration note: --reasoning-compat now defaults to standard, which emits reasoning via delta.reasoning_content / message.reasoning_content instead of injecting <think> tags into content. Set --reasoning-compat think-tags (or GPTMOCK_REASONING_COMPAT=think-tags) to keep the old behavior.

• Python 3.13+
• Paid ChatGPT account (Plus / Pro / Team / Enterprise)
• uv (for uvx usage)

The fastest way to run gptmock. No clone, no install — just uvx.

uvx gptmock login

A browser window will open for ChatGPT OAuth. After login, tokens are saved to ~/.config/gptmock/auth.json.

uvx gptmock serve

The server starts at http://127.0.0.1:8000. Use http://127.0.0.1:8000/v1 as your OpenAI base URL.

uvx gptmock info

alias gptmock='uvx gptmock'

gptmock login
gptmock serve --port 9000
gptmock info

Note: To install directly from the GitHub repository instead of PyPI:

uvx --from "git+https://github.com/rapidrabbit76/GPTMock" gptmock login
uvx --from "git+https://github.com/rapidrabbit76/GPTMock" gptmock serve

No build required — pull the pre-built image and run.

services:
  serve:
    image: rapidrabbit76/gptmock:latest
    container_name: gptmock
    command: ["serve", "--verbose", "--host", "0.0.0.0"]
    ports:
      - "8000:8000"
      - "1455:1455"  # OAuth callback port (needed during first-time login)
    volumes:
      - gptmock-data:/data
    environment:
      - GPTMOCK_HOME=/data
      - GPTMOCK_LOGIN_BIND=0.0.0.0
    healthcheck:
      test: ["CMD-SHELL", "python -c \"import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:8000/health').status==200 else 1)\""]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 120s  # Allows time for first-time login before health checks begin

volumes:
  gptmock-data:

Run the container interactively. If no credentials are found, the login flow starts automatically:

docker compose run --rm --service-ports serve

A URL will be printed in the terminal:

No credentials found. Starting login flow...
Starting local login server on http://localhost:1455
If your browser did not open, navigate to:
  https://auth.openai.com/oauth/authorize?...

If the browser can't reach this machine, paste the full redirect URL here and press Enter:

Two ways to complete login:

1. Browser on the same machine — the URL opens automatically and the OAuth callback is caught on port 1455.
2. Browser on a different machine — open the URL, complete login, then copy the full redirect URL from the browser address bar (starts with http://localhost:1455/auth/callback?code=...) and paste it into the terminal.

Once login succeeds, the server starts automatically.

Once credentials are saved in the volume, just run in the background:

docker compose up -d serve

curl -s http://localhost:8000/health | jq .

All server options below are also available as environment variables. Use the GPTMOCK_* canonical names (see Server Options).

Additional Docker-specific variables:

from openai import OpenAI

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

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

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="http://127.0.0.1:8000/v1",
    api_key="anything",
    model="gpt-5.4",
)
response = llm.invoke("hello world")
print(response.content)

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 world"}]
  }'

Fast variants (*-fast) are synthetic aliases that map to the base model plus service_tier="priority" in the upstream payload. No separate endpoint or auth is required — the ChatGPT backend accepts them as paid-tier priority requests.

Upstream availability note: model availability can change independently of GPTMock releases. GPTMock may recognize a model ID even when the current ChatGPT Codex backend rejects it for a specific account or subscription. On 2026-04-17, direct probe requests against the current upstream accepted gpt-5.2, gpt-5.3-codex, gpt-5.3-codex-spark, gpt-5.4, and gpt-5.4-mini, while rejecting gpt-5, gpt-5.1, gpt-5-codex, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1-codex-max, and gpt-5.2-codex with: The '<model>' model is not supported when using Codex with a ChatGPT account.

• Streaming & Non-streaming — real-time SSE and buffered JSON responses
• Structured Output — response_format with json_schema / json_object support
• Tool / Function Calling — including web search with URL citation annotations via responses_tools
• Thinking Summaries — <think> tags, o3 reasoning format, or legacy mode
• Responses API — POST /v1/responses for LangChain and other clients that auto-route codex models
• Ollama Compatibility — drop-in replacement for Ollama API consumers
• Auto Token Refresh — JWT tokens are refreshed automatically before expiry

gptmock serve [OPTIONS]

Each option can also be set via environment variable. Precedence: CLI flag > GPTMOCK_* env > CHATGPT_LOCAL_* legacy env > default.

Legacy aliases: CHATGPT_LOCAL_REASONING_EFFORT, CHATGPT_LOCAL_REASONING_SUMMARY, CHATGPT_LOCAL_REASONING_COMPAT, CHATGPT_LOCAL_EXPOSE_REASONING_MODELS, CHATGPT_LOCAL_ENABLE_WEB_SEARCH, CHATGPT_LOCAL_DEBUG_MODEL are still accepted as fallbacks.

Use --enable-web-search to enable the web search tool by default for all requests. When enabled, the model decides autonomously whether a query needs a web search. You can also enable web search per-request without the server flag by passing the parameters below.

When web search is active, the model may return annotations containing source URLs. These are included automatically in responses:

Non-streaming (stream: false) — annotations are attached to the message:

{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "SpaceX launched 29 Starlink satellites...",
        "annotations": [
          {
            "type": "url_citation",
            "start_index": 0,
            "end_index": 150,
            "url": "https://spaceflightnow.com/...",
            "title": "SpaceX Falcon 9 launch"
          }
        ]
      }
    }
  ]
}

Streaming (stream: true) — annotations arrive as a dedicated chunk before the final stop chunk:

data: {"choices": [{"delta": {"annotations": [{"type": "url_citation", "start_index": 0, "end_index": 150, "url": "https://...", "title": "..."}]}, "finish_reason": null}]}
data: {"choices": [{"delta": {}, "finish_reason": "stop"}]}

Responses API (POST /v1/responses, non-streaming) — annotations are nested inside the output content:

{
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "SpaceX launched 29 Starlink satellites...",
          "annotations": [
            {
              "type": "url_citation",
              "start_index": 0,
              "end_index": 150,
              "url": "https://spaceflightnow.com/...",
              "title": "SpaceX Falcon 9 launch"
            }
          ]
        }
      ]
    }
  ]
}

curl http://127.0.0.1:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5",
    "messages": [{"role":"user","content":"Find current METAR rules"}],
    "stream": true,
    "responses_tools": [{"type": "web_search"}],
    "responses_tool_choice": "auto"
  }'

• Requires an active, paid ChatGPT account.
• Context length may be partially used by internal system instructions.
• For the fastest responses, set --reasoning-effort to low and --reasoning-summary to none.
• The context size of this route is larger than what you get in the regular ChatGPT app.
• When the model returns a thinking summary, the default standard mode emits reasoning_content fields without polluting content. Set --reasoning-compat think-tags to keep <think> tags for older chat apps, or --reasoning-compat legacy for the older reasoning fields.
• This project is not affiliated with OpenAI. Use responsibly and at your own risk.

• Original project: RayBytes/chatmock
• This fork: rapidrabbit76/GPTMock