MODEL RADAR · OPENROUTER
KI-Modelle auf einen Blick vergleichen.
Alle derzeit bei OpenRouter gelisteten Modelle mit einheitlichen Angaben zu Modalitäten, Kontext, Preisen, Konfiguration und Anbietern.
- KATALOGUMFANG
- ALLE ÖFFENTLICHEN
- Modelle
- 534
- Anbieter
- 75
- zuletzt synchronisiert
- 31.08.2026
qwenQwen: Qwen3 VL 30B A3B Thinking
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...
- Kontext
- 262K
- Eingabe
- text · image
- Ausgabe
- text
qwenQwen: Qwen3 VL 30B A3B Instruct
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
- Kontext
- 262K
- Eingabe
- text · image
- Ausgabe
- text
openaiOpenAI: GPT-5 Pro
GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...
- Kontext
- 400K
- Eingabe
- image · text · file
- Ausgabe
- text
z-aiZ.ai: GLM 4.6
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
- Kontext
- 205K
- Eingabe
- text
- Ausgabe
- text
anthropicAnthropic: Claude Sonnet 4.5
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
- Kontext
- 1M
- Eingabe
- text · image · file
- Ausgabe
- text
anthropicAnthropic: Claude Sonnet 4.5 (batch)
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
- Kontext
- 1M
- Eingabe
- text · image · file
- Ausgabe
- text
deepseekDeepSeek: DeepSeek V3.2 Exp
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
- Kontext
- 164K
- Eingabe
- text
- Ausgabe
- text
thedrummerTheDrummer: Cydonia 24B V4.1
Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.
- Kontext
- 131K
- Eingabe
- text
- Ausgabe
- text
relaceRelace: Relace Apply 3
Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...
- Kontext
- 256K
- Eingabe
- text
- Ausgabe
- text
qwenQwen: Qwen3 VL 235B A22B Thinking
Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....
- Kontext
- 131K
- Eingabe
- text · image
- Ausgabe
- text
qwenQwen: Qwen3 VL 235B A22B Instruct
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
- Kontext
- 262K
- Eingabe
- text · image
- Ausgabe
- text
qwenQwen: Qwen3 Max
Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...
- Kontext
- 262K
- Eingabe
- text
- Ausgabe
- text
qwenQwen: Qwen3 Coder Plus
Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...
- Kontext
- 1M
- Eingabe
- text
- Ausgabe
- text
deepseekDeepSeek: DeepSeek V3.1 Terminus
DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...
- Kontext
- 164K
- Eingabe
- text
- Ausgabe
- text
qwenQwen: Qwen3 Coder Flash
Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...
- Kontext
- 1M
- Eingabe
- text
- Ausgabe
- text
qwenQwen: Qwen3 Next 80B A3B Thinking
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...
- Kontext
- 262K
- Eingabe
- text
- Ausgabe
- text
qwenQwen: Qwen3 Next 80B A3B Instruct
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
- Kontext
- 262K
- Eingabe
- text
- Ausgabe
- text
qwenQwen: Qwen Plus 0728
Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.
- Kontext
- 1M
- Eingabe
- text
- Ausgabe
- text
moonshotaiMoonshotAI: Kimi K2 0905
Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
- Kontext
- 262K
- Eingabe
- text
- Ausgabe
- text
qwenQwen: Qwen3 30B A3B Thinking 2507
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
- Kontext
- 82K
- Eingabe
- text
- Ausgabe
- text
nousresearchNous: Hermes 4 70B
Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...
- Kontext
- 131K
- Eingabe
- text
- Ausgabe
- text
nousresearchNous: Hermes 4 405B
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
- Kontext
- 131K
- Eingabe
- text
- Ausgabe
- text
deepseekDeepSeek: DeepSeek V3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
- Kontext
- 164K
- Eingabe
- text
- Ausgabe
- text
mistralaiMistral: Mistral Medium 3.1
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...
- Kontext
- 131K
- Eingabe
- text · image · file
- Ausgabe
- text