Verfügbare KI-Modelle
Sie sehen bei jedem Modell, wo es läuft
Offene Modelle laufen EU-gehostet bei LLMBase. Bei proprietären Modellen hängen die Verarbeitungsbedingungen vom gewählten Modell ab. Wir zeigen es Ihnen pro Modell, im Chat und über die Inference API.
EU-gehostete offene Modelle
Alle verfügbaren Open-Weight-Modelle, in der EU gehostet. Neueste zuerst.
V4.1 Flash
EU-gehostetDeepSeek
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
GLM 5.3 Flash
EU-gehostetZ.ai
GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...
Qwen3.8 27B
EU-gehostetQwen
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
V4 Pro 0423
EU-gehostetDeepSeek
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Kimi K3
EU-gehostetMoonshotAI
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Kimi K2.7 Code
EU-gehostetMoonshotAI
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
M3
EU-gehostetMiniMax
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
Kimi K2.6
EU-gehostetMoonshotAI
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
gpt-oss-120b
EU-gehostetOpenAI
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
Proprietäre Modelle
Proprietäre Modelle verarbeitet das Unternehmen hinter dem jeweiligen Modell. Die Bedingungen hängen vom Modell ab. Neueste zuerst.
Anthropic
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...
Mistralai
Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...
Gemini 3.8 Flash
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
GPT-6.1 Sol Pro
Openai
**Cost note:** pro mode spends far more...
GPT-6.1 Sol
Openai
GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...
Claude Sonnet 5.5
Anthropic
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...
GPT-6 Luna Pro
Openai
**Cost note:** pro mode spends far more...
Claude Opus 5.5
Anthropic
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
GPT-6 Luna
Openai
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...
SpaceXAI: Grok 4.7
X Ai
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...
GPT-6 Astra Pro
Openai
**Cost note:** pro mode spends far more...
Qwen3.8 Max (0902)
Qwen
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...
GPT-6 Astra
Openai
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...
Qwen3.8 Max Prime
Qwen
Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...
Claude Fable 5.1
Anthropic
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...
Qwen3.8 Flash
Qwen
Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.
Qwen3.8 2.4T A95B
Qwen
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
Qwen3.7 Flash
Qwen
Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...
GPT-5.6 Terra Pro
Openai
**Cost note:** pro mode spends far more...
GPT-5.6 Terra
Openai
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...
Nano Banana 2 (Gemini 3.1 Flash Image)
Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...
Gemini 3.5 Flash Lite
Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.
Qwen3.7 Max
Qwen
Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...
Mistral: Mistral Medium 3.5
Mistralai
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
Qwen3.5 Plus 2026-04-20
Qwen
Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...
Qwen3.6 Flash
Qwen
Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...
GPT-5.5
Openai
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
GPT-5.5 Pro
Openai
GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...
Qwen3.6 27B
Qwen
Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...
Qwen3.7 Plus
Qwen
Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...
Qwen3.8 Omni Flash
Qwen
Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...
GPT-5.4 Image 2
Openai
It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...
Qwen3.6 35B A3B
Qwen
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
Nano Banana Pro (Gemini 3 Pro Image)
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
Sicherer KI-Chat aus Europa
Nutze Claude, ChatGPT und Gemini zusammen mit EU-gehosteten Modellen wie Deepseek, Qwen und Kimi.
EU-gehostete Open-Modelle, eine API
Server in Deutschland und Finnland. Betrieben von einem deutschen Unternehmen nach DSGVO, AVV verfügbar, ISO-27001-zertifizierte Rechenzentren.
So findest du das richtige KI-Modell
Ein praktischer Leitfaden für die Modellwahl nach Use Case.
Modell an Aufgabe anpassen
Allzweckmodelle funktionieren für viele Aufgaben gut. Für Spezialfälle sind Coding-Modelle und Mathe-Modelle oft präziser und günstiger pro Token.
Kontextfenster berücksichtigen
Für lange Dokumente, Codebasen oder lange Konversationen ist die Kontextgröße entscheidend. Modelle reichen von 8K bis über 1M Token. Größere Fenster erlauben mehr Input, erhöhen aber häufig Kosten und Latenz.
Kosten, Geschwindigkeit und Qualität balancieren
Frontier-Modelle liefern Top-Benchmarkwerte, sind aber teurer und oft langsamer. Schnellere, kleinere Modelle können Routineaufgaben bei hoher Last oft günstiger und mit niedrigerer Latenz erledigen.
Open Source vs. proprietär
Open-Weight-Modelle und alle über die LLMBase Inference API verfügbaren Modelle laufen in EU-Rechenzentren. Proprietäre Modelle, die nur im Chat verfügbar sind, verarbeitet der jeweilige Betreiber.
Multimodalität prüfen
Einige Modelle verarbeiten neben Text auch Bilder, Audio oder Dateien. Für Workflows mit Screenshots, Diagrammen oder Audio-Transkripten sind Vision-/Audio-Inputs wichtig. Strukturierte Outputs und Function Calling sind zentral für Agenten.
Benchmarks als Ausgangspunkt nutzen
GPQA, MMLU Pro und HLE messen Wissen und Reasoning. LiveCodeBench und SciCode testen Coding-Praxis. MATH 500 und AIME bewerten mathematisches Lösen. Vergleiche relevante Kategorien und teste zusätzlich mit eigenen Prompts.
Modellkatalog, Preise, Geschwindigkeit und Benchmark-Scores werden regelmäßig aktualisiert. Chat- und API-Zugriff folgen dem jeweiligen Modell, Tarif und Tier.