Security, Compliance & Certifications
GDPR Compliant
EU AI Act Compliant
AI 100% Sovereign
No Training of Models
World Class Models
Product Presentation
Watch our keynote presentation to discover how IG1 AI API delivers World-class AI performance with full data sovereignty — at up to 3x lower cost.
Official benchmark results, compared with frontier models on the same benchmarks: DeepSeek V4.1 Flash posts the highest score in DeepSeek’s comparison table on DeepSWE v1.1, Automation-Bench v1.0.6 and Apex Bench v1.1.
DeepSWE v1.1
DeepSeek V4.1 Flash scores 77.0 on DeepSWE v1.1: the highest score in DeepSeek’s comparison table, ahead of Claude Opus 5 (74.0) and GPT-5.6 Sol (73.0).
Automation-Bench v1.0.6
DeepSeek V4.1 Flash scores 60.5 on Automation-Bench v1.0.6: the highest score in DeepSeek’s comparison table, ahead of Claude Opus 5 (50.3).
Apex Bench v1.1
DeepSeek V4.1 Flash scores 72.1 on Apex Bench v1.1: the highest score in DeepSeek’s comparison table, ahead of Claude Opus 5 (65.8) and GPT-5.6 Sol (54.3).
Scores from DeepSeek’s official model card (V4.1-Flash-1017, October 2026), compared with frontier models on the same benchmarks.
DeepSeek’s frontier open-weight model — a 552B-parameter mixture-of-experts with 8B active parameters on prefill and 16B on decode, a one-million-token context, and native text and image understanding. IG1 AI serves it in France, with zero data retention and transparent per-token pricing.
77.0 on DeepSWE v1.1 for autonomous software engineering: ahead of Claude Opus 5 (74.0) and GPT-5.6 Sol (73.0).
Highest score in DeepSeek’s comparison table on Automation-Bench v1.0.6 (60.5) and on Apex Bench v1.1 (72.1).
A one-million-token context for multi-file coding, deep reasoning and agents that run for hours.
Inference in IG1’s HDS-certified infrastructure in France: zero data retention, no model training on your prompts, EUR invoicing, no US-jurisdiction exposure.
Sovereign inference, in France.
DeepSeek V4.1 Flash is open-weights (MIT) and runs on many providers worldwide. What IG1 AI adds is the contract around it: inference in our HDS-certified infrastructure in France, zero data retention, no training on your prompts, EUR invoicing, and no US-jurisdiction exposure — through the same OpenAI-compatible endpoint as the rest of the catalog, with no Chinese data path either.
1M input tokens
0,65 €
1M cached input
0,13 €
1M output tokens
1,30 €
Context
1M tokens
Benchmark scores from DeepSeek’s official model card (V4.1-Flash-1017, October 2026), compared with frontier models on the same benchmarks.
A filmed testimonial: EasyBourse shares how sovereign AI helps its teams scale software development.
Watch on YouTubeLeveraging the most powerful open-weight models available today. No vendor lock-in. Full transparency.
DeepSeek V4.1 Flash New
by DeepSeek — Hangzhou, China
Flagship LLM
DeepSeek’s frontier open-weight model (552B-parameter MoE, 8B active on prefill and 16B on decode) with native text and image understanding, for deep reasoning, multi-file coding and long-horizon agents.
GLM 5.3 Flash Frontier
by Z.ai — Beijing, China
Efficient Frontier LLM
Efficient frontier model 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.
Transparent per-token pricing. All models are sovereign, hosted in France, with no hidden fees and no minimum commitment.
| Model | Description | 1M Input Tokens | 1M Cached Input Tokens | 1M Output Tokens |
|---|---|---|---|---|
deepseek-v4.1-flash |
DeepSeek’s frontier open-weight model (552B-parameter MoE, 8B active on prefill and 16B on decode) with native text and image understanding, for deep reasoning, multi-file coding and long-horizon agents. Max context: 1M tokens. Served on the 1017 release. | 0,65 € | 0,13 € | 1,30 € |
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 € |
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 € |
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 € |
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 € |
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 €) and on DeepSeek V4.1 Flash (0,13 € vs 0,65 €).
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.
| Model | Description | 1M Input Tokens | 1M Output Tokens |
|---|---|---|---|
| Image generation. Token count based on image resolution and quality level. | 0 € | 0,002 € | |
| 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 € | 0,002 € | |
| Image editing. Token count based on source and generated image resolution and quality level. | 0 € | 0,002 € | |
| 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 € | 0,002 € |
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.
Everything you need to know about IG1 AI API — sovereignty, models, pricing, and getting started.
Sovereignty & Security
Models & Performance
Pricing & Billing
Getting Started