ModelBridge
Simple Multi-Provider LLM Gateway
ModelBridge is a Python library that provides unified access to multiple AI providers. It simplifies working with OpenAI, Anthropic, Google, and Groq APIs through a single interface.
✨ What it Does
- Multi-Provider Support: Works with OpenAI, Groq, Google, and Anthropic
- Smart Model Selection: Automatically picks models based on your task
- Cost Tracking: Shows you how much each request costs
- Simple API: One function (
ask) for most use cases - Environment Variables: Secure API key management
🚀 Quick Start
Installation
pip install modelbridge
Basic Usage
import asyncio
from modelbridge.simple import ask
# Set your API keys as environment variables:
# export OPENAI_API_KEY='your_openai_key'
# export GROQ_API_KEY='your_groq_key'
async def main():
response = await ask("What is the capital of France?")
print(f"Answer: {response.content}")
print(f"Model: {response.model_id}")
print(f"Provider: {response.provider_name}")
print(f"Cost: ${response.cost:.4f}")
asyncio.run(main())
Advanced Usage
# Specify a particular model
response = await ask("Write Python code", model="gpt-4")
# Optimize for speed, cost, or quality
response = await ask("Simple math", optimize_for="cost")
response = await ask("Complex analysis", optimize_for="quality")
# Set maximum cost limit
response = await ask("Quick question", max_cost=0.001)
# Other useful functions
from modelbridge.simple import code, translate, summarize
# Generate code
response = await code("Create a sorting function", language="python")
# Translate text
response = await translate("Hello world", "Spanish")
# Summarize text
response = await summarize("Long article text here...", length="short")
Configuration
API Keys
Set your API keys as environment variables:
# Add the providers you want to use
export OPENAI_API_KEY='sk-your-openai-key'
export GROQ_API_KEY='gsk_your-groq-key'
export GOOGLE_API_KEY='your-google-key'
export ANTHROPIC_API_KEY='sk-ant-your-anthropic-key'
You need at least one API key for ModelBridge to work.
Supported Providers
- OpenAI: GPT-4, GPT-3.5-turbo, GPT-5-mini
- Groq: Llama 3.3 (very fast)
- Google: Gemini models
- Anthropic: Claude models
How It Works
- You call
ask("your question") - ModelBridge analyzes your prompt
- It picks the best model for the task
- Returns response with cost tracking
- Automatically handles errors and retries
License
MIT License
Simple AI provider integration.
Metadata
Release files for modelbridge 0.1.7
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 |
|---|---|---|---|---|
| modelbridge-0.1.7.tar.gz | 229.7 kB | Without provenance | Details for modelbridge-0.1.7.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| modelbridge-0.1.7-py3-none-any.whl | Python 3 | none | any | Details for modelbridge-0.1.7-py3-none-any.whl |
Total release size: 490.2 kB
Release files / modelbridge-0.1.7.tar.gz
| Download URL | modelbridge-0.1.7.tar.gz |
|---|---|
| Size | 229.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8299aadae90a9dfd4f379339f89bfe6132fd4ae7db8c4fffd2cacbd996147c6c
|
|
BLAKE2b-256 checksum How to use checksums |
efa7612f53082d1a8e9dd8d6fc92e59b5430d185cecc189e72c1cd8e18b78bf8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.5
|
Release files / modelbridge-0.1.7-py3-none-any.whl
| Download URL | modelbridge-0.1.7-py3-none-any.whl |
|---|---|
| Size | 260.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1795b77961679e267018c47feeb29d3d2f2233ece7f24d0f3d4a81b7d044b867
|
|
BLAKE2b-256 checksum How to use checksums |
9abf6f05953b170fd3a920252ca1d435e0e7b4f727a742644ebf3aca25f0bbb1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.5
|
Security for modelbridge 0.1.7
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.