Quick AI Coding Examples

English | 简体中文

Runnable examples for integrating developer tools with the Quick AI Coding OpenAI-compatible API. Start with model discovery, then choose the Responses or Chat Completions-compatible example required by your client.

About Quick AI Coding

Quick AI Coding is an independently operated AI API access platform for developers. It provides selected OpenAI-compatible request formats, Responses API-compatible streaming, model discovery, and usage records through a single Base URL.

The platform is designed for development workflows that need:

• integration with Codex CLI, Cursor, Python, Node.js, curl, and clients that accept a custom Base URL;
• SSE streaming for incremental output;
• model discovery through /v1/models before each integration is configured;
• visible platform credit balances and request usage records;
• public pricing for evaluation and ongoing development.

Visit the website · View pricing · Create an account · Read the API guide · Configure Codex CLI

Service terms and regional eligibility apply. The service is not offered to users located in mainland China; review the supported regions policy before registering.

Quick start

1. Create a platform API key in the Quick AI Coding dashboard.

2. Export the key without placing it in source control:

   export QUICKAICODE_API_KEY="your-platform-api-key"
   export QUICKAICODE_BASE_URL="https://quickaicode.com/v1"

3. Discover the model IDs currently available to your account:

   ./curl/list-models.sh

4. Export one returned ID and run a streaming example:

   export QUICKAICODE_MODEL="returned-model-id"
   ./curl/responses-stream.sh

The shell examples require curl and Python 3. To run the SDK example:

python3 -m venv .venv
. .venv/bin/activate
pip install -r python/requirements.txt
python python/responses_stream.py

The dependency-free Node.js example requires Node 20 or newer:

node node/responses-stream.mjs

Examples

Client	Example	Notes
curl	curl/list-models.sh	Discover model IDs before sending requests.
curl	curl/responses-stream.sh	Raw SSE from the Responses-compatible endpoint.
curl	curl/chat-completions.sh	Chat Completions-compatible request.
Python	python/responses_stream.py	Streams typed response events with the OpenAI Python SDK.
Node.js	node/responses-stream.mjs	Uses Node 20 native fetch and parses SSE frames.
Codex CLI	codex/README.md	Custom provider configuration using the Responses wire API.
Cursor	cursor/README.md	Custom API key setup and documented compatibility limits.

Documentation

• English integration overview
• Codex CLI guide
• Cursor guide
• Responses API-compatible guide
• Pricing

Compatibility and service relationship

Quick AI Coding is an independently operated third-party AI API access service. It is not affiliated with, endorsed by, sponsored by, or an official partner of OpenAI or Cursor. "OpenAI-compatible" refers only to selected request and response formats tested by Quick AI Coding; it does not mean full feature parity with the OpenAI API.

Model availability, fields, event types, rates, limits, and service behavior can change. Query /v1/models and consult the current platform documentation before production use. Dollar-denominated amounts shown by Quick AI Coding are internal platform API credits used for usage accounting; they are not OpenAI API account balances and cannot be redeemed as OpenAI credit. Never commit an API key or paste one into an issue.