~/just-llms_

The unifiedLLM gateway.

A production-ready Python library. Superior routing, analytics, and cost optimization.

Pip InstallSource
main.py
from justllms import JustLLM

# Initialize with your API keys
client = JustLLM({
    "providers": {
        "openai": {"api_key": "your-key"},
        "google": {"api_key": "your-key"},
        "anthropic": {"api_key": "your-key"},
        "ollama": {"base_url": "http://localhost:11434"}
    }
})

# Simple completion - uses configured fallback or first available provider
response = client.completion.create(
    messages=[{"role": "user", "content": "Explain quantum computing briefly"}]
)
print(response.content)
60%
COST REDUCTION
7+
PROVIDERS
1.1MB
PACKAGE SIZE
Zero
DEPENDENCIES

System Specifications.

Automatic Fallbacks

Configure fallback models. If a provider goes down, requests are reliably re-routed instantly.

Provider-Agnostic Tools

Define tools once with @tool and use them seamlessly across OpenAI, Anthropic, and Google.

SXS Model Comparison

Interactive CLI tool to compare latency, tokens, and output side-by-side simultaneously.

Native Tools

Out-of-the-box support for Server-Side Google Search and sandboxed Python Code Execution.

Zero Config

Installs in seconds. No complex YAML chains or heavy dependency bloat. Native Ollama support.