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.

OpenAI + Anthropic compatibility

Both API surfaces come from the same router. The two are not separate products — they're two doors into the same model pool, same pricing, same API key, same usage dashboard. Use whichever client your stack already speaks.

Base URLs

The same API key works for both. Pick the URL that matches your SDK.

Quick integration

Drop-in compatible with both SDKs. The base URL is the only thing that changes — the rest of your code stays the same.

from openai import OpenAI client = OpenAI(    base_url="https://api.IQXtokenfactory.com/openai/v1/",    api_key="tf-your-api-key-here",) response = client.chat.completions.create(    model="meta-llama/Llama-3.3-70B-Instruct",    messages=[{"role": "user", "content": "Hello!"}],) print(response.choices[0].message.content)

import anthropic client = anthropic.Anthropic(    base_url="https://api.IQXtokenfactory.com/anthropic/",    api_key="tf-your-api-key-here",) message = client.messages.create(    model="claude-3-5-sonnet-20241022",    max_tokens=1024,    messages=[{"role": "user", "content": "Explain quantum entanglement"}],) print(message.content[0].text)

import OpenAI from "openai"; const client = new OpenAI({  baseURL: "https://api.IQXtokenfactory.com/openai/v1/",  apiKey: "tf-your-api-key-here",}); const response = await client.chat.completions.create({  model: "meta-llama/Llama-3.3-70B-Instruct",  messages: [{ role: "user", content: "Hello!" }],}); console.log(response.choices[0].message.content);

import Anthropic from "@anthropic-ai/sdk"; const client = new Anthropic({  baseURL: "https://api.IQXtokenfactory.com/anthropic/",  apiKey: "tf-your-api-key-here",}); const message = await client.messages.create({  model: "claude-3-5-sonnet-20241022",  max_tokens: 1024,  messages: [{ role: "user", content: "Hello!" }],}); console.log(message.content[0].text);

Key concepts

Quickstart

First response in under 2 minutes. Pick the SDK you already have.

Step 1 — Install the SDK

# Python — pick onepip install openaipip install anthropic# Node.jsnpm i openainpm i @anthropic-ai/sdk

Step 2 — Set your API key

Get a key from the dashboard, then set it in your environment. Onetf-key works for both endpoints.

export IQX_API_KEY="tf-your-api-key-here"

Step 3 — Make your first request

from openai import OpenAIimport osclient = OpenAI(    base_url="https://api.IQXtokenfactory.com/openai/v1/",    api_key=os.environ["IQX_API_KEY"],)response = client.chat.completions.create(    model="meta-llama/Llama-3.3-70B-Instruct",    messages=[{"role": "user", "content": "Hello from IQx Token Factory!"}],)print(response.choices[0].message.content)

Choose a model

Browse the full 33-model catalog with pricing, context length, and TPS on the Models page.

Authentication

A single tf- API key authorizes both the OpenAI and Anthropic endpoints. Pass it in whichever header your SDK expects.

Key format

Authorization: Bearer tf-your-api-key-here

x-api-key: tf-your-api-key-hereanthropic-version: 2023-06-01

Response headers

Every response includes rate-limit headers. Use them to back off gracefully.

X-RateLimit-Limit-Requests: 60X-RateLimit-Remaining-Requests: 59X-RateLimit-Reset-Requests: 30sX-RateLimit-Limit-Tokens: 1000000X-RateLimit-Remaining-Tokens: 999872X-RateLimit-Reset-Tokens: 0s

Error codes

IQx Token Factory uses standard HTTP status codes. The response shape matches the SDK that issued the request — OpenAI SDK calls return OpenAI-style error envelopes, Anthropic SDK calls return Anthropic-style envelopes.

Cross-SDK error handling

Streaming

Set stream=true on chat or messages calls and the response comes back as Server-Sent Events. Each chunk carries a delta you can forward to the user interface as it arrives.

from openai import OpenAI client = OpenAI(    base_url="https://api.IQXtokenfactory.com/openai/v1/",    api_key="tf-your-api-key-here",) stream = client.chat.completions.create(    model="meta-llama/Llama-3.3-70B-Instruct",    stream=True,    messages=[{"role": "user", "content": "Write a haiku about inference."}],) for chunk in stream:    delta = chunk.choices[0].delta.content    if delta:        print(delta, end="", flush=True)