Now live — DeepSeek R1-0528 reasoning · UltraFast LPU inference available in all plansNew models liveExplore →

IQx Token Factory · Frontier Inference Platform

Frontier inference,
one endpoint.

IQx Token Factory is the inference layer for modern AI — 33 open-source and frontier models through one OpenAI- and Anthropic-compatible API, with transparent per-token pricing and zero infrastructure to manage.

$npx@iqx/token-factory init

Start building Explore models

✓OpenAI & Anthropic SDK compatible✓Claude Code & Codex ready✓ 99.9% uptime SLA

/ The Model Matrix

Four flagship surfaces.
One API underneath.

Browse all 33 models

Flagship · Reasoning

Pro Reasoning

Frontier chain-of-thought models — DeepSeek V4 Pro, GLM-5.1, Qwen3.5-397B. Transparent per-token billing, 1M context on flagships.

11 modelsFrom $0.07 / M tokens

Flagship · Speed

UltraFast LPU

Latency-critical inference on Language Processing Unit silicon. Up to 1,800 TPS for real-time agents, code completion, and interactive tools.

7 modelsSub-100ms TTFT

Open Source

Open Models

Production-grade open models from Qwen, Meta, Google, NVIDIA, and more. Apache 2.0 / Llama / Open-license, deployable anywhere.

11 modelsFrom $0.06 / M tokens

Vision

Vision Models

Multimodal models with image + text understanding. Document Q&A, chart parsing, OCR, screenshot-to-code, and visual reasoning at production scale.

3 modelsUp to 1M context

Plus 1 embeddings model for semantic search, RAG, and similarity tasks. View the embeddings model →

1,000,000Tokens on the $3 plan

$3Test plan / 24 hours

1Credit card required

25Models unlocked

Get your Opus Million tokens today.

Your million tokens from $3, same plan.

Claim your million tokens From $3 · See plans & pricing

Serving models from

DeepSeek

Meta Llama

Qwen

OpenAI

Z.ai GLM

xAI

Google

Moonshot

NVIDIA

OpenAI OSSPrime Intellect

NousResearchOpenBMB

DeepSeek

Meta Llama

Qwen

OpenAI

Z.ai GLM

xAI

Google

Moonshot

NVIDIA

OpenAI OSSPrime Intellect

NousResearchOpenBMB

/ The Platform

Built for production
from the first request.

Full architecture

Unified API

One endpoint. Every modality.

Text, reasoning, code, vision, embeddings, and open-source general models — all through one OpenAI- and Anthropic-compatible interface. Swap providers by changing one URL.

# OpenAI & Anthropic compatible, drop-in
from openai import OpenAI
client = OpenAI(
  base_url="https://api.IQXtokenfactory.com/v1/",
  api_key="tf-•••••")

Read the quickstart →

Throughput

1,000TPS

Peak tokens per second on GPT OSS 20B UltraFast

Latency

<100ms

Time-to-first-token under load

UltraFast Models

Tokens per second

GPT OSS 20B1,000

Llama 3.1 8B840

Qwen3 32B662

Llama 4 Scout594

See benchmark details →

Open Models

11 open-license models, deployable anywhere

Apache 2.0, Llama, and Open-licensed. Qwen, Meta Llama, NVIDIA Nemotron, Google Gemma, and more.

Browse open models →

Pricing

From $3. No idle GPU cost.

1M-token test plan, monthly windows, or pure pay-as-you-go.

View plans →

SLA

99.9%

Uptime backed by multi-region failover

Caching

50% off cached input

On GPT OSS models — automatic prompt caching.

Compat

Drop-in OpenAI & Anthropic

Works with every OpenAI and Anthropic SDK out of the box.

/ Why IQx Token Factory

One platform. Every workload. Zero lock-in.

From your first prototype to multi-region production scale, the same API, the same billing model, the same observability stack.

Performance

UltraFast LPU inference

Up to 1,000 tokens per second on Language Processing Unit silicon. Sub-100ms time-to-first-token, even at peak load.

Compatibility

OpenAI & Anthropic compatible, drop-in

Works with every OpenAI SDK, every Anthropic SDK, the Vercel AI SDK, LangChain, LlamaIndex, the OpenAI CLI, and Claude Code. Change one base URL — keep the rest.

Pricing

Transparent per-token billing

No idle GPU cost, no minimums, no surprise overage. Stripe billing, Odoo finance sync, line-item invoices for every request.

Catalog

33 models, one API

Reasoning, code, multilingual, vision, embeddings, and open-source general models. Frontier and open-source, all under one key.

Reliability

99.9% SLA, multi-region

Automatic failover across three regions, real-time health monitoring, and a public status page. Your apps stay up.

Developer experience

First-class SDKs

Python, TypeScript, Go, and Rust SDKs. Type hints, streaming, retries, and full observability baked in. Five lines to your first request.

/ By the numbers

Built for teams that ship.

12B+

Tokens served daily

60+

Models in catalog

99.97%

Uptime last 90 days

14K+

Active developers

/ Latest Updates

Shipped this month.

View changelog

Model · ReasoningNEW

DeepSeek V4 Pro — chain-of-thought at frontier parity

1M context, $2.10 / $4.20 per M tokens (+20% markup). Now serving in production with stable latency.

Jun 2026DeepSeekReasoning

Infra · IQx ultra fastNEW

LPU silicon — 1,800 TPS on GPT OSS 20B

7 IQx ultra fast models now live on Language Processing Unit silicon. Sub-100ms TTFT under load.

May 2026IQx ultra fastThroughput

PricingUPDATE

Token Plan — $3 test plan with 1M tokens

Credit card required. Predictable monthly windows from $25. Pure PAYG for scale.

May 2026StripeOdoo

Start at $3.
Ship your first agent today.

Start at $3 →Read the docs

/ One-Line Setup

Set up your IDE in 30 seconds.

Run one command. Paste your API key. IQx Token Factory auto-configures Claude Code, Codex, and every model in your workspace based on the plan you're on — no env files, no boilerplate.

Auto-detects your IDE — Claude Code, Cursor, Codex CLI, Continue, Cline, or any OpenAI/Anthropic-compatible client.
Plan-aware model routing — picks the right default model, context window, and rate limit for your tier (Test, Pro, Max, Ultra).
Writes the env file for you — .env.local with OPENAI_BASE_URL, ANTHROPIC_BASE_URL, and IQX_API_KEY in one shot.
Safe to re-run — upgrades are idempotent. Existing keys, custom models, and overrides are preserved.

CLI · v1.2.0

Install with npx

Works on macOS, Linux, and Windows. Node 18+ required.

terminal

# Install the IQx Token Factory CLI & set up your workspace

$ npx @iqx/token-factory init

# Paste your API key when prompted

? Enter your IQx Token Factory API key: tf-****-****-****-a3f9

# Pick your IDE

? Detected: Claude Code · Gemini CLI · OpenAI CLI

› All of the above

# Models are routed by your plan

✓ Plan: Max · 5M / 5-hour window

✓ Default model: claude-opus-4-8 (Top frontier · Anthropic)

✓ Context window: 1M

✓ Endpoint: https://api.IQXtokenfactory.com/v1

✓ Wrote .env.local · .claude/settings.json · .gemini/config.json · .openai/config.json

✓ You're ready. Run claude, gemini, or openai to start.

~ 1.4 MB · MIT licensed

$npx@iqx/token-factory init

✓ Test✓ Pro✓ Max✓ Ultra

Four flagship surfaces.One API underneath.

Pro Reasoning

UltraFast LPU

Open Models

Vision Models

Get your Opus Million tokens today.

Built for productionfrom the first request.

One endpoint. Every modality.

Tokens per second

11 open-license models, deployable anywhere

From $3. No idle GPU cost.

50% off cached input

Drop-in OpenAI & Anthropic

One platform. Every workload. Zero lock-in.

UltraFast LPU inference

OpenAI & Anthropic compatible, drop-in

Transparent per-token billing

33 models, one API

99.9% SLA, multi-region

First-class SDKs

Built for teams that ship.

Shipped this month.

DeepSeek V4 Pro — chain-of-thought at frontier parity

LPU silicon — 1,800 TPS on GPT OSS 20B

Token Plan — $3 test plan with 1M tokens

Start at $3.Ship your first agent today.

Set up your IDE in 30 seconds.

Install with npx

Four flagship surfaces.
One API underneath.

Built for production
from the first request.

Start at $3.
Ship your first agent today.