22 models on the appliance
Open-weight models out of the box, for chat, code and embeddings.
You decide where your data is processed. Open-weight models such as Qwen, Mistral and gpt-oss run on the appliance, and your data stays on the device. Hosting in Germany adds larger models, and in On Demand external ones too, depending on your plan.
Free for 3 days, hosted in Germany
up to 51models, hosted in Germany
As of October 2026, 51 models in the catalogue.
Open-weight models out of the box, for chat, code and embeddings.
Larger models from Mistral AI, with no hardware of your own.
In On Demand depending on your plan, processed in the providers' EU tenants without storing your input. Not connected with Air-Gap.
You decide: the appliance, hosting in Germany or, in On Demand depending on plan, external models too.
You decide which model answers, on the appliance according to tasks and concurrent users.
Models stay in a fixed version, and new ones arrive as tested packages that apply after your approval.
51 of 51 models
| Model | Type | Context window | Max. output | Deployment |
|---|---|---|---|---|
| Mistral Small 4Mistral AI | Chat | 256,000 | – | Local |
| Ministral 3 8BMistral AI | Chat | 256,000 | – | Local |
| Devstral Small 2Mistral AI | Code | 256,000 | – | Local |
| Magistral Small 1.2Mistral AI | Chat | 128,000 | – | Local |
| Qwen3.6-35B-A3BQwen (Alibaba) | Chat | 256,000 | – | Local |
| Qwen3.6-27BQwen (Alibaba) | Chat | 256,000 | – | Local |
| Qwen3-Coder-30B-A3BQwen (Alibaba) | Code | 262,144 | – | Local |
| Qwen3-30B-A3B-2507Qwen (Alibaba) | Chat | 262,144 | – | Local |
| Qwen3-14BQwen (Alibaba) | Chat | 32,768 | – | Local |
| Qwen3-8BQwen (Alibaba) | Chat | 32,768 | – | Local |
| Qwen3 Embedding 8BQwen (Alibaba) | Embedding | – | – | Local |
| Gemma 4Google | Chat | 128,000 | – | Local |
| Gemma 3 27BGoogle | Chat | 128,000 | – | Local |
| gpt-oss-120bOpenAI | Chat | 131,072 | 131,072 | Local |
| gpt-oss-20bOpenAI | Chat | 131,072 | 131,072 | Local |
| Llama 4 ScoutMeta | Chat | 10,000,000 | – | Local |
| Llama 3.3 70BMeta | Chat | 128,000 | – | Local |
| Llama 3.1 8BMeta | Chat | 128,000 | – | Local |
| Phi-4Microsoft | Chat | 16,384 | – | Local |
| Phi-4-reasoning-plusMicrosoft | Chat | 32,768 | – | Local |
| Llama 3.3 Nemotron Super 49BNVIDIA | Chat | 128,000 | – | Local |
| Nemotron Nano 9B v2NVIDIA | Chat | 128,000 | – | Local |
| Mistral Large 3Mistral AI | Chat | 256,000 | – | Hosted in Germany |
| Mistral Medium 3.5Mistral AI | Chat | 256,000 | – | Hosted in Germany |
| CodestralMistral AI | Code | 256,000 | – | Hosted in Germany |
| Mistral EmbedMistral AI | Embedding | – | – | Hosted in Germany |
| DeepSeek V4-ProDeepSeek | Chat | 1,000,000 | – | External · EU/ZDR |
| DeepSeek V4-FlashDeepSeek | Chat | 1,000,000 | – | External · EU/ZDR |
| Claude Fable 5.1Anthropic | Chat | 1,000,000 | 128,000 | External · EU/ZDR |
| Claude Fable 5Anthropic | Chat | 1,000,000 | 128,000 | External · EU/ZDR |
| Claude Opus 5.5Anthropic | Chat | 1,000,000 | 128,000 | External · EU/ZDR |
| Claude Opus 5Anthropic | Chat | 1,000,000 | 128,000 | External · EU/ZDR |
| Claude Opus 4.8Anthropic | Chat | 1,000,000 | 128,000 | External · EU/ZDR |
| Claude Sonnet 5Anthropic | Chat | 1,000,000 | 128,000 | External · EU/ZDR |
| Claude Haiku 4.5Anthropic | Chat | 200,000 | 64,000 | External · EU/ZDR |
| Gemini 3.1 ProGoogle | Chat | 1,000,000 | 64,000 | External · EU/ZDR |
| Gemini 3.5 FlashGoogle | Chat | 1,000,000 | 64,000 | External · EU/ZDR |
| Gemini 3.1 Flash-LiteGoogle | Chat | 1,000,000 | 64,000 | External · EU/ZDR |
| Gemini Embedding 2Google | Embedding | – | – | External · EU/ZDR |
| GPT-5.6 SolOpenAI | Chat | 1,050,000 | 128,000 | External · EU/ZDR |
| GPT-5.6 TerraOpenAI | Chat | 1,050,000 | 128,000 | External · EU/ZDR |
| GPT-5.6 LunaOpenAI | Chat | 1,050,000 | 128,000 | External · EU/ZDR |
| GPT-5.5OpenAI | Chat | 1,050,000 | 128,000 | External · EU/ZDR |
| GPT-5.4OpenAI | Chat | 1,050,000 | 128,000 | External · EU/ZDR |
| GPT-5.4 miniOpenAI | Chat | 400,000 | 128,000 | External · EU/ZDR |
| GPT-5.1OpenAI | Chat | 400,000 | 128,000 | External · EU/ZDR |
| GPT-5OpenAI | Chat | 400,000 | 128,000 | External · EU/ZDR |
| GPT Image 2OpenAI | Image | – | – | External · EU/ZDR |
| GLM-5.2Z.ai (GLM) | Chat | 1,000,000 | 128,000 | External · EU/ZDR |
| Kimi K2.6Moonshot AI (Kimi) | Chat | 256,000 | – | External · EU/ZDR |
| MiniMax-M3MiniMax | Chat | 1,000,000 | – | External · EU/ZDR |
In On Demand, external models are paid for with AI credits and processed in the providers' EU and zero data retention tenants. On-premise, they can be enabled optionally, with the provider's token costs. Not with Air-Gap Enterprise. As of October 2026.
Request a modelModels run in fixed versions and are not trained further on your content.
New versions arrive as tested packages and only replace the old one after your approval.
We test an open-weight model with a commercial licence on the reference appliance and add it to your profile.
Question not listed? Call us: +49 3744 365 2202
You decide. On the appliance, the selection depends on your tasks and the number of concurrent users.
In On Demand depending on your plan. On Private Spark as an option, with the provider's token costs. Your document base is not transferred.
Free for 3 days, then from €24.90 per user per month. Cancellable monthly.