IG1 | AI API — Sovereign AI, World-Class Performance

Performance

Numbers That Set
a New Standard.

World-class AI models powering enterprise workloads. Built on the most powerful open-weight models available today.

AIME 2026 Math Reasoning

91.3% Benchmark

World-class scores on advanced mathematical reasoning benchmarks.

—Extended multi-step reasoning
—Built on Qwen 3.5 open-weight models
—No data retention, fully sovereign

Context Window

256K tokens

Industry-leading context window enabling enterprise-scale document processing and long-chain reasoning.

—Process thousands of pages per prompt
—Ideal for RAG, legal & compliance
—Optimized memory efficiency

Zero CapEx to Start

$0 upfront investment

Skip the massive GPU cluster investment. Access enterprise-grade sovereign AI instantly via API.

—No $500K–$1M GPU CAPEX required
—No $200K/year AI staff overhead
—Instant API access, zero setup

Use Cases

What Does This Mean
for Your Team?

Everyone in your team can adopt AI — not just your engineers. Marketing, sales, analysts, developers. IG1 AI API meets you where you are.

Chat

Integrate conversational AI into any application. Build smart assistants, customer support bots, and interactive workflows.

Code

Ship features faster with AI-assisted development. Generate, review, refactor and debug code at enterprise scale.

Summarize

Transform thousands of documents into actionable insights. Extract, condense, and analyze enterprise knowledge at scale.

Create

Generate content and analysis at scale. From marketing copy to financial reports, empower every department with AI-powered creation.

Data Sovereignty

What About
Your Data?

The question every enterprise asks. IG1 AI API is built precisely for this. Your security team says yes. Your legal team says yes. And you can move fast with confidence.

Zero Data Retention

Your prompts are processed, then immediately erased. Nothing is stored, nothing is logged.

No Model Training

We never use your data to train models. Your intellectual property belongs to you.

100% Sovereign

Your data never leaves your enterprise boundaries. Fully compliant with GDPR, EU AI Act, and ISO 27001.

Your Prompt

IG1 AI Processes

Immediately Erased

No logs • No storage • No training

Advanced Capabilities

Not Just Compliance.
Real Capability.

IG1 AI API is designed to go further. Enterprise-grade AI built for the way you work.

Extended Thinking

Complex, multi-step reasoning for advanced problem-solving. Chain-of-thought processing for nuanced enterprise scenarios.

Web Search & Tool Use

Integrated real-time web search and connected workflows. Let your AI agents interact with external tools and data sources.

Secure Computer Use

Code execution and secure computer use for true agentic automation. Let AI operate in sandboxed environments safely.

Open-Weight Models

Powered by the
Best Open Models.

Leveraging the most powerful open-weight models available today. No vendor lock-in. Full transparency.

Kimi K2.5 Soon

by Moonshot AI — Beijing, China

LLM & Reasoning

Chat, code, extended thinking, multi-step reasoning. World-class performance.

Qwen 3.5

by Alibaba Cloud — Hangzhou, China

LLM & Coding

Advanced reasoning, code generation, and multi-turn conversation. Frontier-class open-weight model.

Qwen Image

by Alibaba Cloud — Hangzhou, China

Vision & Multimodal

Image understanding, visual analysis, and multimodal reasoning for enterprise workflows.

BGE

by BAAI — Beijing, China

Embedding & Reranking

Semantic search, RAG pipelines, and intelligent document retrieval for enterprise data.

Model Pricing

Our Models

Transparent per-token pricing. No hidden fees, no minimum commitment.

Language Models

Model	Description	1M Input Tokens	1M Output Tokens
Qwen3.5-397B-A17B	General purpose model (GPT 5 / Gemini 3 class). Capabilities: text, code, OCR/vision. Max context: 256K tokens.	1,20 €	5,00 €
Qwen3.5-397B-A17B Creative	Same as Qwen3.5-397B-A17B with hyperparameters forced for creativity. Use Qwen3.5-397B-A17B if you want to control hyperparameters.	1,20 €	5,00 €
Qwen3.5-397B-A17B Thinking	Same as Qwen3.5-397B-A17B with thinking mode enforced. Max context: 256K tokens.	1,20 €	5,00 €
Qwen3.5-397B-A17B Thinking Coder	Same as Qwen3.5-397B-A17B with code specialist and thinking enforced. Max context: 256K tokens.	1,20 €	5,00 €
Kimi K2.5-1T-A32B Roadmap	Specialized in development. Ideal for project planning, user stories, product ideation, coding. Capabilities: text, code, OCR/vision. Max context: 256K tokens.	1,20 €	5,00 €
Kimi K2.5-1T-A32B Thinking Roadmap	Same as Kimi K2.5-1T-A32B with thinking mode enforced. Max context: 256K tokens.	1,20 €	5,00 €
BGE-m3	Text embeddings for RAG and semantic search.	0,05 €	N/A
BGE-reranker-v2-m3	Reranking for search result optimization.	0,30 €	N/A
Document	Convert any document in Markdown to be used by LLM. Useful for CAG – Cached RAG including vision RAG use cases. Document images uses IG1 Standard to be described as text.	N/A	2,00 €

Image Models

Model	Description	1M Input Tokens	1M Output Tokens
Qwen Image	Image generation. Token count based on image resolution and quality level.	N/A	0,002 €
Qwen Image PE	Image generation with Prompt Enhancing by LLM. Prompt enhancement uses Qwen3.5-397B-A17B (charged separately). Token count based on resolution and quality level.	N/A	0,002 €
Qwen Image Edit	Image editing. Token count based on source and generated image resolution and quality level.	0,002 €	0,002 €
Qwen Image Edit PE	Image editing with Prompt Enhancing by LLM. Prompt enhancement uses Qwen3.5-397B-A17B (charged separately). Token count based on source and generated image resolution and quality.	0,002 €	0,002 €

	Self-Hosting	IG1 AI API
GPU CAPEX	$500K – $1M	$0
Specialized Staff	~$200K / year	$0
Infrastructure	Months of setup	Instant
R&D Overhead	Significant	None
Time to Value	6–12 months	Day one

Get Started

Access IG1 AI API
Today.

Get your access keys. Integrate in minutes. Test fast. Scale with confidence.

1. Get Keys

Request your API access keys from our team.

2. Integrate

Connect in minutes with our OpenAI-compatible API.

3. Scale

Test fast, iterate, and scale with confidence.

Get API Access Now

FAQ

Frequently Asked
Questions.

Everything you need to know about IG1 AI API — sovereignty, models, pricing, and getting started.

Sovereignty & Security

Where is my data hosted?

Exclusively in IG1’s own facilities in France, on Dell Technologies and NVIDIA hardware. Your data never leaves our European infrastructure.

Do you retain or use my data to train models?

No. Zero data retention. Zero data training. Zero data sharing. When your request is processed, it’s gone. Period.

Is IG1 AI compliant with GDPR?

Yes. Also ISO 27001 and the EU AI Act. Our air-gapped architecture is designed for compliance by default.

How is this different from using ChatGPT, Claude or Gemini?

OpenAI, Anthropic, and Google are US companies subject to US jurisdiction (including the CLOUD Act). Your data transits through and may be stored on US infrastructure. With IG1 AI, your data stays in France, under European law, with zero retention, zero data sharing, zero data training.

Models & Performance

What models does IG1 AI use?

We run the best open-weights models available. Our model catalog includes: IG1 Standard (general purpose), IG1 Thinking (extended reasoning), IG1 Dev (development specialist), IG1 Embedding, IG1 Reranking, and IG1 Image (generation and editing). All models support up to 256K token context windows.

Can I choose which model to use?

Yes. You can select the specific IG1 model that fits your task — Standard for general use, Thinking for complex reasoning, Dev for coding and product work, Image for visual content. Or let IG1 AI route automatically.

Pricing & Billing

How does pricing work?

Simple flat monthly subscription (IG1 AI Usage Capacity). You get unlimited access to all IG1 AI models up to your token cap. One invoice per month. No per-token billing surprises, no overages.

What happens if I hit my cap?

Access pauses until the next billing cycle. No overage charges, ever. If you consistently hit your cap, we’ll discuss upgrading your plan.

Why flat-rate instead of pay-per-token?

Because you’re starting with AI and need predictable costs. Token-based billing creates anxiety and discourages adoption. Flat-rate means your whole team can experiment freely without watching a meter.

Is there a free trial?

Getting Started

How long does setup take?

Zero infrastructure setup on your side. You can be live the same day.

Do I need a technical team to use IG1 AI?

No. IG1 AI is designed for every team — marketing, sales, HR, legal, analysts, and developers. If you can use a chat interface, you can use IG1 AI.

Can I integrate IG1 AI into my existing tools?

Yes. IG1 AI provides API access compatible with standard AI chat applications (Msty, Open WebUI) and IDE integrations for developers. Connect your existing workflows without changing your tools.

What if a better AI platform comes along?

No lock-in. Flat monthly billing means you can leave anytime. But because we continuously upgrade to the best open-weights models, you’re always on the frontier without switching.

We Are Opening
Our AI.

See IG1 AI API
in Action.

Numbers That Set
a New Standard.

What Does This Mean
for Your Team?

Chat