inferenceiq 0.1.0

InferenceIQ - AI inference cost optimization. Drop-in replacement for OpenAI SDK.

InferenceIQ Python SDK

Drop-in replacement for the OpenAI Python SDK that automatically optimizes every inference request — cutting costs by up to 40% with intelligent model routing, semantic caching, and prompt compression.

Installation

pip install inferenceiq

Quick Start

from inferenceiq import InferenceIQ

# Drop-in OpenAI replacement
client = InferenceIQ(api_key="iq-live_...")

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

Features

• OpenAI-compatible: Swap openai.OpenAI() for InferenceIQ() — same API
• Automatic cost optimization: Intelligent model routing saves 25-40%
• Semantic caching: Identical/similar requests served from cache
• Quality guarantees: Set minimum quality thresholds per request
• Full observability: Per-request cost attribution and savings tracking

Native API

# Use the native optimization API for more control
result = client.optimize(
    prompt="Summarize this document...",
    strategy="balanced",        # cost_optimized | balanced | quality_first | latency_optimized
    quality_threshold=0.85,
    max_cost_per_token=0.00003
)

print(f"Saved: ${result.savings:.4f}")
print(f"Provider: {result.provider_used}")

Links

• Dashboard: https://inferenceiq.onrender.com
• API Docs: https://inferenceiq-api.onrender.com/docs
• GitHub: https://github.com/awh233/inferenceiq