NewOpenAI- and Anthropic-compatible — no migrationRead the announcement →
v1.0 · Live

IQx Token Factory API

A unified inference API for 33 open-source and frontier models — from lightweight LLMs to vision, code, reasoning, and embeddings. Switch the base URL in your existing OpenAI or Anthropic SDK and run on IQx Token Factory infrastructure. No new SDK to learn, no migration to plan.

Get an API keyBrowse 33 models

Introduction

IQx Token Factory is a unified inference platform. The same API key, the same usage dashboard, the same pricing — across both OpenAI-style/openai/v1/and Anthropic-style/anthropic/v1/endpoints.

We aggregate access to a curated set of 33 open-source and proprietary models. Use any of them with the client library you already have.

Now serving both OpenAI and Anthropic endpoints.

One API key works for both the /openai/v1/ and /anthropic/v1/ surfaces. Switch the base_url in your existing SDK — no migration, no new client.

OpenAI + Anthropic

Two endpoints. One router. Both are first-class. The same key, the same billing, the same usage feed.

  • OpenAI compatible: /openai/v1/ — works with the official openai SDK, openai-node, langchain-openai, and most tooling that targets the OpenAI API.
  • Anthropic compatible: /anthropic/v1/ — works with the official @anthropic-ai/sdk and any tooling that targets the Anthropic Messages API.

Base URLs

OpenAIhttps://api.IQXtokenfactory.com/openai/v1/
Anthropichttps://api.IQXtokenfactory.com/anthropic/v1/

Quick integration

Python · OpenAI
from openai import OpenAIclient = OpenAI(    base_url="https://api.IQXtokenfactory.com/openai/v1/",    api_key="tf-your-api-key-here",)print(client.chat.completions.create(    model="meta-llama/Llama-3.3-70B-Instruct",    messages=[{"role": "user", "content": "Hi!"}],).choices[0].message.content)
Python · Anthropic
import anthropicclient = anthropic.Anthropic(    base_url="https://api.IQXtokenfactory.com/anthropic/",    api_key="tf-your-api-key-here",)print(client.messages.create(    model="claude-3-5-sonnet-20241022",    max_tokens=1024,    messages=[{"role": "user", "content": "Hi!"}],).content[0].text)

Key concepts

⚙

API keys

Bearer tokens starting with tf-. Get yours from the Dashboard.

$

Token billing

Billed per token — input and output separately. See the Models page for per-model rates.

⚡

UltraFast

Models flagged UltraFast run on LPU silicon — up to 1,800 tokens/sec.

⏱

Rate limits

Vary by plan. Check X-RateLimit-* and retry-after headers.