Developers

    The shortest path from model to production.

    One OpenAI-compatible interface for frontier models, dedicated endpoints, and infrastructure you control.

    Start with the API
    python
    from openai import OpenAI

client = OpenAI(
  base_url="https://api.inferx.com/v1",
  api_key="ix_..."
)

response = client.chat.completions.create(
  model="meta/llama-3.3-70b",
  messages=[{"role": "user", "content": "Hello"}]
)

    Quickstart

    Three steps. One endpoint.

    1. 01Create an API key
    2. 02Choose a model
    3. 03Send your first request
    shell
    # Install the SDK
pip install openai

# Point your existing client at InferX
export OPENAI_BASE_URL=https://api.inferx.com/v1
export OPENAI_API_KEY=ix_your_key

    Models

    Browse context windows, capabilities, and pricing.

    SDKs

    Python, TypeScript, and OpenAI-compatible clients.

    API Reference

    Complete schemas for every endpoint and event.

    Playground

    Compare models and prompts side by side.

    Benchmarks

    Latency, throughput, and efficiency data.

    Examples

    Patterns for agents, RAG, tools, and streaming.

    Build something production-ready.

    Read the documentation