ainative-openai
Drop-in replacement for the OpenAI Python SDK that routes to AINative's free API — Llama, Qwen, DeepSeek, and Kimi models with zero configuration.
Install
pip install ainative-openai
Quick Start
Replace from openai import OpenAI with from ainative_openai import OpenAI. That's it.
from ainative_openai import OpenAI
client = OpenAI() # auto-provisions a free API key
response = client.chat.completions.create(
model="meta-llama/Llama-3.3-70B-Instruct",
messages=[{"role": "user", "content": "Explain quantum computing in 3 sentences."}],
)
print(response.choices[0].message.content)
First run auto-provisions a free API key (72h expiry) and saves it to ~/.ainative/config.json. Follow the printed claim URL to get a permanent key.
Async
import asyncio
from ainative_openai import AsyncOpenAI
async def main():
client = AsyncOpenAI()
response = await client.chat.completions.create(
model="qwen3-coder-flash",
messages=[{"role": "user", "content": "Write a Python fibonacci generator"}],
)
print(response.choices[0].message.content)
asyncio.run(main())
Streaming
from ainative_openai import OpenAI
client = OpenAI()
stream = client.chat.completions.create(
model="deepseek-4-flash",
messages=[{"role": "user", "content": "Write a haiku about code"}],
stream=True,
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="")
Tool Calling
from ainative_openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="meta-llama/Llama-3.3-70B-Instruct",
messages=[{"role": "user", "content": "What's the weather in Austin?"}],
tools=[{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get weather for a city",
"parameters": {
"type": "object",
"properties": {"city": {"type": "string"}},
"required": ["city"],
},
},
}],
)
Available Models
| Model | ID |
|---|---|
| Llama 3.3 70B | meta-llama/Llama-3.3-70B-Instruct |
| Llama 4 Scout | meta-llama/Llama-4-Scout-17B-16E-Instruct |
| Qwen3 Coder Flash | qwen3-coder-flash |
| DeepSeek 4 Flash | deepseek-4-flash |
| Kimi K2 | kimi-k2 |
All models are free on AINative's API.
Authentication Priority
The client resolves API keys in this order:
api_keyargumentAINATIVE_API_KEYenvironment variableOPENAI_API_KEYenvironment variable- Saved key in
~/.ainative/config.json - Auto-provision via instant-db (free, 72h expiry)
Configuration
# Explicit key
client = OpenAI(api_key="your-ainative-key")
# Custom base URL (self-hosted)
client = OpenAI(api_key="key", base_url="http://localhost:8000/v1")
# Environment variables
# AINATIVE_API_KEY=your-key
# AINATIVE_BASE_URL=https://custom.endpoint/v1
Migrating from OpenAI
- from openai import OpenAI
+ from ainative_openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
- model="gpt-4",
+ model="meta-llama/Llama-3.3-70B-Instruct",
messages=[{"role": "user", "content": "Hello!"}],
)
Every feature of the official openai SDK works — this is a thin subclass that only changes the defaults.
License
MIT
Metadata
Release files for ainative-openai 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ainative_openai-0.1.0.tar.gz | 7.8 kB | Without provenance | Details for ainative_openai-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ainative_openai-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for ainative_openai-0.1.0-py3-none-any.whl |
Total release size: 14.8 kB
Release files / ainative_openai-0.1.0.tar.gz
| Download URL | ainative_openai-0.1.0.tar.gz |
|---|---|
| Size | 7.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6346e9025f62d98b325581c8c8466166b8583aa71a46ad535f8916833d1dac52
|
|
BLAKE2b-256 checksum How to use checksums |
1b39dbabb16fd7886268f127ce95946fb1dd64e1fecb9ab642ed25db7ee8d507
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.2
|
Release files / ainative_openai-0.1.0-py3-none-any.whl
| Download URL | ainative_openai-0.1.0-py3-none-any.whl |
|---|---|
| Size | 6.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0184265b9a60a595ef890c6adb54f20bb17c08122217d51c4b2c4a5af9a8d95a
|
|
BLAKE2b-256 checksum How to use checksums |
ab04719ba0c84e5524ee75ef38ec3d881e7adb594d873f352e9f3118bdd0b0b6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.2
|
Security for ainative-openai 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.