IG1 | AI API — Sovereign Frontier AI, Hosted in France

Performance

GLM 5.3 Flash
Performance Signals.

Official GLM 5.3 Flash benchmarks highlight autonomous software engineering, a one-million-token context, and native multimodal input.

DeepSWE v1.1

63.4 software engineering benchmark

GLM 5.3 Flash scores 63.4 on DeepSWE v1.1 in Z.ai’s official benchmark table, which measures autonomous resolution of real-world software engineering tasks.

—Autonomous software engineering
—320B MoE architecture, 18B active parameters
—No data retention, fully sovereign
—Frontier reasoning through IG1 AI API

Context Window

1M tokens

GLM 5.3 Flash supports an official one-million-token context window and up to 128K output tokens, making it suitable for long documents, large codebases, and multi-step agent workflows.

—1M-token official context length
—Up to 128K output tokens
—Hybrid sparse and linear attention

Native Multimodal

320B parameters — 18B active

GLM 5.3 Flash is the first natively multimodal model in the GLM-5 series: video, image, text, and file input in a sparse MoE architecture with 18 billion active parameters.

—Video, image, text, and file input
—3.01× less attention compute vs GLM-5.3
—4.44× smaller KV cache vs GLM-5.3
—Open weights under MIT licence

Efficient Frontier

GLM 5.3 Flash.
The Flagship.

GLM 5.3 Flash is the efficient frontier model of IG1 AI API: a natively multimodal reasoning, coding, and agentic execution engine with a one-million-token context, delivered with sovereign inference and transparent per-token pricing.

Model	Positioning	Best for	Offered by IG1 AI
Efficient model	Compact MoE	High-volume production workloads	✓ Qwen 3.6 35B
Efficient frontier	Efficient	World-class reasoning, code, and agents	✓ GLM 5.3 Flash

What GLM 5.3 Flash changes in practice

GLM 5.3 Flash is built for tasks where quality, precision, and persistence matter more than a quick generic answer. Here's where the difference is immediately visible:

Long contract analysis

GLM 5.3 Flash follows cross-references, nested clauses, exceptions, and definitions across very long documents — up to a one-million-token context — and accepts scanned pages and images as readily as text.

Multi-file code generation

From architecture planning to implementation details, GLM 5.3 Flash is tuned for coherent multi-file development, refactoring, and debugging, scoring 63.4 on DeepSWE v1.1 for autonomous software engineering.

Multi-constraint reasoning

Budget, timeline, stack, compliance, security, UX, scalability: GLM 5.3 Flash keeps simultaneous constraints active and turns them into clear decisions.

Complex instructions over long context

For long prompts with nested requirements, GLM 5.3 Flash is the model to use when your team needs the answer to stay faithful to every instruction through the end of the generation.

Why choose GLM 5.3 Flash?

Use GLM 5.3 Flash when the work is strategic: hard reasoning, product ideation, advanced coding, agentic planning, deep analysis, and documents and media where small mistakes are expensive. It also offers the best capability per euro in the IG1 AI catalog — the default choice for everyday work too.

Frontier performance, transparent token pricing

GLM 5.3 Flash is the flagship model of the catalogue, with the best capability per euro: 0,35 € / 1M input tokens (0,09 € cached) and 1,15 € / 1M output tokens. Qwen 3.6 35B completes the catalogue for high-volume production workloads at 0,30 € (0,06 € cached) / 1,00 €.

Efficient Model

Qwen 3.6 35B.
Efficient, Production Ready.

GLM 5.3 Flash is the flagship model. Qwen 3.6 35B is the efficient tier: a Mixture-of-Experts model built for high-volume production traffic at the lowest token price in the catalog — available in three profiles: Instruct, Thinking and Thinking Coder.

Sparse Mixture-of-Experts

Qwen 3.6 35B engages about 3 billion of its 35 billion parameters per token: fast responses and a compact inference footprint, with a 256K-token context.

Built for production traffic

At 0,30 € input (0,06 € cached) and 1,00 € output per 1M tokens, Qwen 3.6 35B is the most affordable model in the IG1 AI catalog — built for production traffic, internal copilots, and high-volume agent pipelines.

Production-grade versatility

Use it for chat, coding assistance, structured extraction, summarization, and tool-using agents when frontier-level reasoning is not required.

Three profiles, one price

Instruct for fast everyday answers, Thinking for structured reasoning, Thinking Coder for development workflows — all three at the same 0,30 € / 1,00 € rate, selected per request by model ID, without touching your budget.

Use case	Recommended model	Why
Hard reasoning, strategic coding, complex agents	GLM 5.3 Flash	Maximum capability, 1M-token context
Production chat, extraction, copilots, high-volume agents	Qwen 3.6 35B	Lowest token price in the catalog
Step-by-step reasoning and analysis	Qwen 3.6 35B Thinking	Thinking mode enforced, same price
Coding assistance and refactoring at volume	Qwen 3.6 35B Thinking Coder	Tuned for development workflows, same price
Hybrid routing	GLM + Qwen	GLM by default, Qwen where its profile fits

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

Open-Weight Models

Powered by the
Best Open Models.

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

GLM 5.3 Flash Frontier

by Z.ai — Beijing, China

Efficient Frontier LLM

The flagship of our catalogue for reasoning, code and agentic workflows — with the best capability per euro.

Qwen 3.6

by Alibaba Cloud — Hangzhou, China

35B-A3B LLM

Efficient Mixture-of-Experts model for production chat, code, reasoning, and high-volume workflows.

Qwen Image

by Alibaba Cloud — Hangzhou, China

Image Generation & Editing

Image generation and editing from text prompts, with optional LLM prompt enhancement.

Qwen3-VL-Embedding-8B SOTA

by Alibaba Cloud — Hangzhou, China

Multimodal Embedding

State-of-the-art retrieval with multimodal embeddings and dynamic dimensions up to 4096 — far beyond fixed-size text encoders.

BGE

by BAAI — Beijing, China

Fast Embedding & Reranking

Fast, fixed-dimension text embeddings and reranking — a quality reference for high-throughput semantic search and RAG pipelines.

Model Pricing

Our Models

Transparent per-token pricing. All models are sovereign, hosted in France, with no hidden fees and no minimum commitment.

Language Models

Model	Description	1M Input Tokens	1M Cached Input Tokens	1M Output Tokens
GLM-5.3-Flash`glm53-flash-chat`	Natively multimodal efficient frontier model (video, image, text, file) for reasoning, code and agentic workflows. Max context: 1M tokens, 128K output. Also available as glm53-flash-chat-low, glm53-flash-agent and glm53-flash-agent-low at the same price.	0,35 €	0,09 €	1,15 €
Qwen 3.6 35B`qwen36-35b-a3b-instruct`	Efficient Mixture-of-Experts model (35B parameters, 3B active) for production chat, code, extraction, and multi-turn workflows. Default instruct profile. Max context: 256K tokens.	0,30 €	0,06 €	1,00 €
Qwen 3.6 35B Thinking`qwen36-35b-a3b-thinking-general`	Same as Qwen 3.6 35B with thinking mode enforced for structured reasoning and analysis.	0,30 €	0,06 €	1,00 €
Qwen 3.6 35B Thinking Coder`qwen36-35b-a3b-thinking-coding`	Qwen 3.6 35B configured for advanced coding, refactoring, debugging, and thinking-enforced development workflows.	0,30 €	0,06 €	1,00 €
BGE-m3	Text embeddings for RAG and semantic search.	0,05 €	N/A	N/A
BGE-reranker-v2-m3	Reranking for search result optimization.	0,30 €	N/A	N/A
Qwen3-VL-Embedding-8B	Multimodal embeddings (text and images) for RAG and visual semantic search.	0,30 €	N/A	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 are described as text by Qwen 3.6 35B.	N/A	N/A	2,00 €

Why cached input tokens save you money

When an AI agent works on a task — reviewing code, fixing a bug across files, running a long conversation — it sends the same context again and again: your instructions, the files it is working on, everything said so far. Only a small part is actually new each time.

With input caching, IG1 AI keeps what it has already read and processes only what is new. Responses start sooner, and the repeated context is billed at the cached input rate — about a quarter of the normal input price on GLM 5.3 Flash (0,09 € vs 0,35 €), a fifth on Qwen 3.6 35B (0,06 € vs 0,30 €).

Example — an agentic coding session on GLM 5.3 Flash: 100 API calls, ~20,000 tokens of context re-sent at each call, 65% cache hit rate.

	Without caching	With caching
Input tokens billed at full rate	2.0 M	0.7 M
Input tokens billed at cached rate	—	1.3 M
Input cost	0,70 €	0,36 €
Session total (incl. 25K output tokens)	0,73 €	0,39 €

−48% on input cost, −46% on the session — and a faster first token.

Caching is automatic on every IG1 AI language model — nothing to configure. Each response’s token usage shows exactly how many input tokens were served from the cache.

Image Models

Model	Description	1M Output Tokens
Qwen Image	Image generation. Token count based on image resolution and quality level.	0,002 €
Qwen Image PE	Image generation with Prompt Enhancing by LLM. Prompt enhancement uses Qwen 3.6 35B (charged separately). Token count based on resolution and quality level.	0,002 €
Qwen Image Edit	Image editing. Token count based on source and generated image resolution and quality level.	0,002 €
Qwen Image Edit PE	Image editing with Prompt Enhancing by LLM. Prompt enhancement uses Qwen 3.6 35B (charged separately). Token count based on source and generated image resolution and quality.	0,002 €

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

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 sovereign, EU-hosted architecture with strict no-data-retention guarantees 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-weight models available, led by GLM 5.3 Flash for frontier reasoning, coding, and agentic workflows. The catalog also includes Qwen 3.6 35B for efficient high-volume language tasks, Qwen3-VL-Embedding-8B and BGE for embeddings and reranking, and Qwen Image for visual generation.

Can I choose which model to use?

Yes. Choose GLM 5.3 Flash — the most capable model in the catalog — for frontier reasoning and coding, Qwen 3.6 35B (Instruct, Thinking or Thinking Coder) for high-volume production workloads at the lowest token price, or the dedicated Qwen3-VL-Embedding-8B / BGE embedding and reranking models and Qwen Image for specialized tasks.

Are your models quantized?

Yes — deliberately, and chosen to preserve quality. Where a higher-precision release exists (e.g. Qwen), we serve FP8: the quality impact is negligible while GPU memory and cost are roughly halved, which is the right engineering trade-off. When a frontier model is only released quantized, we serve it at its native precision. What we never do is push aggressive low-bit quantization that would degrade the hardest tasks (multi-step reasoning, complex document analysis, large-scale code generation). The benchmark figures we publish reflect the exact precision we serve in production.

Pricing & Billing

How does pricing work?

Two parts. A flat 100 € / month subscription that includes 100 € of usage across every model in the catalog. Beyond that, usage is metered at the published per-token rates (GLM 5.3 Flash at 0,35 € input, 0,09 € cached input and 1,15 € output; Qwen 3.6 35B at 0,30 € input, 0,06 € cached input and 1,00 € output), up to a monthly ceiling of 1 000 € on the 100 € subscription (the ceiling scales with your tier). No hidden fees. Context re-sent across calls is billed at the cached input rate — see Why cached input tokens save you money.

What happens if I hit my cap?

Your monthly ceiling is 1 000 € on the 100 € subscription, and scales with higher tiers. When you reach it, access pauses until the next billing cycle — or until you settle that amount. You are never charged beyond the ceiling you control. If you consistently hit it, we’ll discuss raising your limit.

How is overage billed?

On the 1st of each month we bill the previous month’s overage — usage above your included allowance — together with the coming month’s subscription. Payment is by SEPA direct debit or saved card.

Why a subscription plus metered usage?

You get the predictability of a fixed monthly base and the flexibility to scale when a project demands it — no renegotiation. Light months stay light, heavy months stay capped. You only pay for what you use, up to a ceiling you set.

Can I commit to a higher plan?

Yes. Higher monthly subscription tiers — with a larger included allowance and ceiling — are available for teams that need more. Contact sales to arrange a commitment that fits your volume.

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. Monthly billing with no commitment means you can leave anytime. But because we continuously upgrade to the best open-weights models, you’re always on the frontier without switching.

Sovereign AI API.
Frontier Models.
Zero Data Leakage.

See IG1 AI API
in Action.

GLM 5.3 Flash
Performance Signals.