KI-Modelle
Alle Modelle mit verfügbaren Preisdaten, gruppiert nach Modell-ID, Anzeige-Name und Cloud/API-Anbieter.
Modellname ist nicht gleich Abrechnungsweg
Ein Modell wie GPT, Claude, Gemini oder Llama kann direkt beim Modellanbieter, über Azure AI Foundry, Google Cloud / Vertex AI, AWS Bedrock oder STACKIT verfügbar sein. Für Kosten, Datenschutz und Betrieb zählt daher neben dem Modell auch die gewählte Cloud/API-Route.
Modellübersicht
| Modell-ID | Name | Anbieter |
|---|---|---|
| anthropic.claude-haiku-4-5 | Claude Haiku 4.5 | Anthropic |
| anthropic.claude-opus-4-1 | Claude Opus 4.1 | Anthropic |
| anthropic.claude-opus-4-5 | Claude Opus 4.5 | Anthropic |
| anthropic.claude-opus-4-6 | Claude Opus 4.6 | Anthropic |
| anthropic.claude-opus-4-7 | Claude Opus 4.7 | Anthropic |
| anthropic.claude-sonnet-4-5 | Claude Sonnet 4.5 | Anthropic |
| anthropic.claude-sonnet-4-6 | Claude Sonnet 4.6 | Anthropic |
| aws.amazon-nova-lite | Amazon Nova Lite | AWS Bedrock |
| aws.amazon-nova-micro | Amazon Nova Micro | AWS Bedrock |
| aws.amazon-nova-pro | Amazon Nova Pro | AWS Bedrock |
| aws.amazon-titan-embed-text | Amazon Titan Text Embeddings | AWS Bedrock |
| aws.amazon-titan-embed-text-v2 | Amazon Titan Text Embeddings V2 | AWS Bedrock |
| aws.claude-2.1-inference | Claude 2.1 Inference | AWS Bedrock |
| aws.claude-instant-inference | Claude Instant Inference | AWS Bedrock |
| aws.cohere-command | Cohere Command | AWS Bedrock |
| aws.cohere-command--light | Cohere Command – Light | AWS Bedrock |
| aws.deepseek-v3.1 | DeepSeek-V3.1 | AWS Bedrock |
| aws.deepseek-v3.2 | DeepSeek-V3.2 | AWS Bedrock |
| aws.devstral-2-123b | Devstral 2 123B | AWS Bedrock |
| aws.gemma-3-12b | Gemma 3 12B | AWS Bedrock |
| aws.gemma-3-27b | Gemma 3 27B | AWS Bedrock |
| aws.gemma-3-4b | Gemma 3 4B | AWS Bedrock |
| aws.gpt-oss-120b | gpt-oss-120b | AWS Bedrock |
| aws.gpt-oss-20b | gpt-oss-20b | AWS Bedrock |
| aws.kimi-k2-thinking | Kimi K2 Thinking | AWS Bedrock |
| aws.kimi-k2.5 | Kimi K2.5 | AWS Bedrock |
| aws.llama-2-chat-13b | Llama 2 Chat (13B) | AWS Bedrock |
| aws.llama-2-chat-70b | Llama 2 Chat (70B) | AWS Bedrock |
| aws.llama-2-pre-trained-13b | Llama 2 Pre-trained (13B) | AWS Bedrock |
| aws.llama-2-pre-trained-70b | Llama 2 Pre-trained (70B) | AWS Bedrock |
| aws.minimax-m2 | Minimax M2 | AWS Bedrock |
| aws.minimax-m2.1 | Minimax M2.1 | AWS Bedrock |
| aws.minimax-m2.5 | Minimax M2.5 | AWS Bedrock |
| aws.mistral-large-3 | Mistral Large 3 | AWS Bedrock |
| aws.nvidia-nemotron-3-nano-30b-a3b | NVIDIA Nemotron 3 Nano 30B A3B | AWS Bedrock |
| aws.nvidia-nemotron-3-super-120b-a12b | NVIDIA Nemotron 3 Super 120B A12B | AWS Bedrock |
| aws.nvidia-nemotron-nano-2 | NVIDIA Nemotron Nano 2 | AWS Bedrock |
| aws.nvidia-nemotron-nano-2-vl | NVIDIA Nemotron Nano 2 VL | AWS Bedrock |
| aws.qwen3-coder-next | Qwen3 Coder Next | AWS Bedrock |
| aws.qwen3-next-80b-a3b | Qwen3 Next 80B A3B | AWS Bedrock |
| aws.qwen3-vl-235b-a22b | Qwen3 VL 235B A22B | AWS Bedrock |
| azure.code-fast-1 | Code Fast 1 | Azure AI Foundry |
| azure.codestral | Codestral | Azure AI Foundry |
| azure.codex-mini | Codex mini | Azure AI Foundry |
| azure.cohere-command-a | Cohere Command A | Azure AI Foundry |
| azure.cohere-embed-v4-txt | Cohere Embed v4 Txt | Azure AI Foundry |
| azure.deepseek-mai-ds-r1 | DeepSeek MAI DS R1 | Azure AI Foundry |
| azure.deepseek-r1 | DeepSeek R1 | Azure AI Foundry |
| azure.deepseek-v3 | DeepSeek V3 | Azure AI Foundry |
| azure.deepseek-v3-0324 | DeepSeek V3 0324 | Azure AI Foundry |
| azure.deepseek-v3.1 | DeepSeek V3.1 | Azure AI Foundry |
| azure.deepseek-v3.2 | DeepSeek V3.2 | Azure AI Foundry |
| azure.deepseek-v3.2-sp | DeepSeek V3.2 SP | Azure AI Foundry |
| azure.embedding-ada | embedding ada | Azure AI Foundry |
| azure.fireworks-deepseek-v3.2 | Fireworks DeepSeek V3.2 | Azure AI Foundry |
| azure.fireworks-deepseek-v4-pro | Fireworks DeepSeek V4 Pro | Azure AI Foundry |
| azure.fireworks-glm-5 | Fireworks GLM 5 | Azure AI Foundry |
| azure.fireworks-glm-5.1 | Fireworks GLM 5.1 | Azure AI Foundry |
| azure.fireworks-gpt-oss-120b | Fireworks GPT-OSS-120B | Azure AI Foundry |
| azure.fireworks-kimi-k2.5 | Fireworks Kimi K2.5 | Azure AI Foundry |
| azure.fireworks-kimi-k2.6 | Fireworks Kimi K2.6 | Azure AI Foundry |
| azure.fireworks-minimax-2.7 | Fireworks MiniMax 2.7 | Azure AI Foundry |
| azure.fireworks-minimax-m2.5 | Fireworks MiniMax M2.5 | Azure AI Foundry |
| azure.gpt-35-turbo | GPT-3.5 Turbo | Azure AI Foundry |
| azure.gpt-4-turbo | GPT-4 Turbo | Azure AI Foundry |
| azure.gpt-4-turbo128k | GPT-4 turbo128K | Azure AI Foundry |
| azure.gpt-4.1 | GPT-4.1 | Azure AI Foundry |
| azure.gpt-4.1-mini | GPT-4.1 mini | Azure AI Foundry |
| azure.gpt-4.1-nano | GPT-4.1 nano | Azure AI Foundry |
| azure.gpt-4.5-0227 | GPT-4.5 0227 | Azure AI Foundry |
| azure.gpt-4o | GPT-4o | Azure AI Foundry |
| azure.gpt-4o-0513 | GPT-4o 0513 | Azure AI Foundry |
| azure.gpt-4o-0806 | GPT-4o 0806 | Azure AI Foundry |
| azure.gpt-4o-1120 | GPT-4o 1120 | Azure AI Foundry |
| azure.gpt-4o-mini | GPT-4o mini | Azure AI Foundry |
| azure.gpt-4o-mini-0718 | GPT-4o mini 0718 | Azure AI Foundry |
| azure.gpt-5 | GPT-5 | Azure AI Foundry |
| azure.gpt-5-codex | GPT-5 Codex | Azure AI Foundry |
| azure.gpt-5-mini | GPT-5 Mini | Azure AI Foundry |
| azure.gpt-5-nano | GPT-5 Nano | Azure AI Foundry |
| azure.gpt-5-pro | GPT-5 pro | Azure AI Foundry |
| azure.gpt-5.1 | GPT-5.1 | Azure AI Foundry |
| azure.gpt-5.1-codex | GPT-5.1 Codex | Azure AI Foundry |
| azure.gpt-5.1-codex-max | GPT-5.1 Codex max | Azure AI Foundry |
| azure.gpt-5.1-codex-mini | GPT-5.1 Codex mini | Azure AI Foundry |
| azure.gpt-5.2 | GPT-5.2 | Azure AI Foundry |
| azure.gpt-5.2-codex | GPT-5.2 Codex | Azure AI Foundry |
| azure.gpt-5.2-pro | GPT-5.2 pro | Azure AI Foundry |
| azure.gpt-5.3-codex | GPT-5.3 Codex | Azure AI Foundry |
| azure.gpt-5.4 | GPT-5.4 | Azure AI Foundry |
| azure.gpt-5.4-longco | GPT-5.4 LongCo | Azure AI Foundry |
| azure.gpt-5.4-mini | GPT-5.4 mini | Azure AI Foundry |
| azure.gpt-5.4-nano | GPT-5.4 nano | Azure AI Foundry |
| azure.gpt-5.4-pro | GPT-5.4 pro | Azure AI Foundry |
| azure.gpt-5.4-pro-longco | GPT-5.4 pro LongCo | Azure AI Foundry |
| azure.gpt-5.5-longco | GPT-5.5 LongCo | Azure AI Foundry |
| azure.gpt-5.5-shortco | GPT-5.5 ShortCo | Azure AI Foundry |
| azure.gpt-oss-120b | GPT-OSS-120B | Azure AI Foundry |
| azure.grok-3 | Grok 3 | Azure AI Foundry |
| azure.grok-3-mini | Grok 3 Mini | Azure AI Foundry |
| azure.grok-4 | Grok 4 | Azure AI Foundry |
| azure.grok-4.1 | Grok 4.1 | Azure AI Foundry |
| azure.grok-4.2 | Grok 4.2 | Azure AI Foundry |
| azure.grok4-fast | Grok4 Fast | Azure AI Foundry |
| azure.kimi-k2-thinking | Kimi K2 Thinking | Azure AI Foundry |
| azure.kimi-k2.5-thinking | Kimi K2.5 Thinking | Azure AI Foundry |
| azure.kimi-k2.6-thinking | Kimi K2.6 Thinking | Azure AI Foundry |
| azure.llama-3.3-70b | Llama 3.3 70B | Azure AI Foundry |
| azure.llama-4-maverick-17b | Llama 4 Maverick 17B | Azure AI Foundry |
| azure.meta-llama-3.1-405b-instruct | Meta Llama 3.1 405B Instruct | Azure AI Foundry |
| azure.meta-llama-3.1-70b-instruct | Meta Llama 3.1 70B Instruct | Azure AI Foundry |
| azure.mistral-large-2407 | Mistral Large 2407 | Azure AI Foundry |
| azure.mistral-large-3 | Mistral Large 3 | Azure AI Foundry |
| azure.o1 | o1 | Azure AI Foundry |
| azure.o1-1217 | o1 1217 | Azure AI Foundry |
| azure.o1-mini | o1-mini | Azure AI Foundry |
| azure.o1-preview | o1-preview | Azure AI Foundry |
| azure.o1-pro | o1-pro | Azure AI Foundry |
| azure.o3-0416 | o3 0416 | Azure AI Foundry |
| azure.o3-mini | o3-mini | Azure AI Foundry |
| azure.o3-mini-0131 | o3-mini 0131 | Azure AI Foundry |
| azure.o3-pro | o3-pro | Azure AI Foundry |
| azure.o4-mini | o4-mini | Azure AI Foundry |
| azure.o4-mini-0416 | o4-mini 0416 | Azure AI Foundry |
| azure.phi-4 | Phi-4 | Azure AI Foundry |
| azure.text-embedding-3-large | text embedding 3 large | Azure AI Foundry |
| azure.text-embedding-3-small | text embedding 3 small | Azure AI Foundry |
| google.claude-4.6-sonnet | Claude 4.6 Sonnet | Google Cloud / Vertex AI |
| google.claude-opus-4.5 | Claude Opus 4.5 | Google Cloud / Vertex AI |
| google.claude-opus-4.6 | Claude Opus 4.6 | Google Cloud / Vertex AI |
| google.claude-opus-4.7 | Claude Opus 4.7 | Google Cloud / Vertex AI |
| google.claude-sonnet-4.5 | Claude Sonnet 4.5 | Google Cloud / Vertex AI |
| google.gemini-1.5-flash-gt-128k | Gemini 1.5 Flash (>128K Kontext) | Google Cloud / Vertex AI |
| google.gemini-1.5-flash-lte-128k | Gemini 1.5 Flash (<=128K Kontext) | Google Cloud / Vertex AI |
| google.gemini-1.5-pro-gt-128k | Gemini 1.5 Pro (>128K Kontext) | Google Cloud / Vertex AI |
| google.gemini-1.5-pro-lte-128k | Gemini 1.5 Pro (<=128K Kontext) | Google Cloud / Vertex AI |
| google.gemini-2.0-flash | Gemini 2.0 Flash | Google Cloud / Vertex AI |
| google.gemini-2.0-flash-lite | Gemini 2.0 Flash Lite | Google Cloud / Vertex AI |
| google.gemini-2.5-flash | Gemini 2.5 Flash | Google Cloud / Vertex AI |
| google.gemini-2.5-flash-lite | Gemini 2.5 Flash Lite | Google Cloud / Vertex AI |
| google.gemini-2.5-pro-gt-200k | Gemini 2.5 Pro (>200K Kontext) | Google Cloud / Vertex AI |
| google.gemini-2.5-pro-lte-200k | Gemini 2.5 Pro (<=200K Kontext) | Google Cloud / Vertex AI |
| google.gemini-3-flash-preview | Gemini 3 Flash Preview | Google Cloud / Vertex AI |
| google.gemini-3-pro-preview | Gemini 3 Pro Preview | Google Cloud / Vertex AI |
| google.gemini-3.1-flash-image-preview | Gemini 3.1 Flash Image Preview | Google Cloud / Vertex AI |
| google.gemini-3.1-flash-lite | Gemini 3.1 Flash-Lite | Google Cloud / Vertex AI |
| google.gemini-3.1-pro-preview-gt-200k | Gemini 3.1 Pro Preview (>200K Kontext) | Google Cloud / Vertex AI |
| google.gemini-3.1-pro-preview-lte-200k | Gemini 3.1 Pro Preview (<=200K Kontext) | Google Cloud / Vertex AI |
| google.gemini-embedding | Gemini Embedding | Google Cloud / Vertex AI |
| google.gemini-embedding-2-multimodal-preview | Gemini Embedding 2 multimodal preview | Google Cloud / Vertex AI |
| google.gpt-oss-120b | gpt-oss-120b | Google Cloud / Vertex AI |
| google.gpt-oss-20b | gpt-oss-20b | Google Cloud / Vertex AI |
| google.imagen-4 | Imagen 4 | Google Cloud / Vertex AI |
| google.imagen-4-fast | Imagen 4 Fast | Google Cloud / Vertex AI |
| google.imagen-4-ultra | Imagen 4 Ultra | Google Cloud / Vertex AI |
| google.llama-3.3-70b | Llama 3.3 70B | Google Cloud / Vertex AI |
| google.multilingual-e5-large | multilingual-e5-large | Google Cloud / Vertex AI |
| google.multilingual-e5-small | multilingual-e5-small | Google Cloud / Vertex AI |
| google.qwen3-235b-a22b-instruct-2507 | Qwen3-235B-A22B-Instruct-2507 | Google Cloud / Vertex AI |
| google.qwen3-coder-480b-a35b-instruct | Qwen3-Coder-480B-A35B-Instruct | Google Cloud / Vertex AI |
| google.qwen3-next-80b-instruct | Qwen3-Next-80B-Instruct | Google Cloud / Vertex AI |
| google.qwen3-next-80b-thinking | Qwen3-Next-80B-Thinking | Google Cloud / Vertex AI |
| google.speech-to-text-v2-dynamic-batch | Speech-to-Text V2 Dynamic Batch | Google Cloud / Vertex AI |
| google.speech-to-text-v2-standard | Speech-to-Text V2 Standard | Google Cloud / Vertex AI |
| google.text-to-speech-chirp-3-hd | Text-to-Speech Chirp 3 HD | Google Cloud / Vertex AI |
| google.text-to-speech-neural2 | Text-to-Speech Neural2 | Google Cloud / Vertex AI |
| google.text-to-speech-wavenet | Text-to-Speech WaveNet | Google Cloud / Vertex AI |
| google.veo-2 | Veo 2 | Google Cloud / Vertex AI |
| google.veo-3 | Veo 3 | Google Cloud / Vertex AI |
| google.veo-3-fast | Veo 3 Fast | Google Cloud / Vertex AI |
| google.veo-3.1 | Veo 3.1 | Google Cloud / Vertex AI |
| google.veo-3.1-fast | Veo 3.1 Fast | Google Cloud / Vertex AI |
| google.veo-3.1-lite | Veo 3.1 Lite | Google Cloud / Vertex AI |
| ionos.bge-large-en-v1.5 | bge-large-en-v1.5 | IONOS Cloud AI Model Hub |
| ionos.bge-m3 | bge-m3 | IONOS Cloud AI Model Hub |
| ionos.flux-1-schnell | FLUX.1 [schnell] | IONOS Cloud AI Model Hub |
| ionos.gpt-oss-120b | gpt-oss-120b | IONOS Cloud AI Model Hub |
| ionos.lightonocr-2 | LightOnOCR 2 | IONOS Cloud AI Model Hub |
| ionos.llama-3.1-405b-instruct | Llama 3.1 405B Instruct | IONOS Cloud AI Model Hub |
| ionos.llama-3.1-8b-instruct | Llama 3.1 8B Instruct | IONOS Cloud AI Model Hub |
| ionos.llama-3.3-70b-instruct | Llama 3.3 70B Instruct | IONOS Cloud AI Model Hub |
| ionos.mistral-nemo-instruct | Mistral Nemo Instruct | IONOS Cloud AI Model Hub |
| ionos.mistral-small-24b-instruct | Mistral Small 24B Instruct | IONOS Cloud AI Model Hub |
| ionos.paraphrase-multilingual-mpnet-base-v2 | paraphrase-multilingual-mpnet-base-v2 | IONOS Cloud AI Model Hub |
| ionos.qwen3-coder-next-80b | Qwen3-Coder-Next (80B) | IONOS Cloud AI Model Hub |
| mistral.codestral | Codestral | Mistral AI |
| mistral.ministral-3-14b | Ministral 3 14B | Mistral AI |
| mistral.ministral-3-8b | Ministral 3 8B | Mistral AI |
| mistral.mistral-embed | Mistral Embed | Mistral AI |
| mistral.mistral-large-3 | Mistral Large 3 | Mistral AI |
| mistral.mistral-medium-3.1 | Mistral Medium 3.1 | Mistral AI |
| mistral.mistral-small-4 | Mistral Small 4 | Mistral AI |
| openai.gpt-3.5-turbo | GPT-3.5 Turbo | OpenAI |
| openai.gpt-4-turbo | GPT-4 Turbo | OpenAI |
| openai.gpt-4.1 | GPT-4.1 | OpenAI |
| openai.gpt-4.1-mini | GPT-4.1 mini | OpenAI |
| openai.gpt-4.1-nano | GPT-4.1 nano | OpenAI |
| openai.gpt-4o | GPT-4o | OpenAI |
| openai.gpt-4o-mini | GPT-4o mini | OpenAI |
| openai.gpt-4o-mini-transcribe | GPT-4o mini Transcribe | OpenAI |
| openai.gpt-4o-transcribe | GPT-4o Transcribe | OpenAI |
| openai.gpt-5.3-codex | GPT-5.3 Codex | OpenAI |
| openai.gpt-5.4 | GPT-5.4 | OpenAI |
| openai.gpt-5.4-mini | GPT-5.4 mini | OpenAI |
| openai.gpt-5.4-nano | GPT-5.4 nano | OpenAI |
| openai.gpt-5.4-pro | GPT-5.4 pro | OpenAI |
| openai.gpt-5.5 | GPT-5.5 | OpenAI |
| openai.gpt-5.5-pro | GPT-5.5 pro | OpenAI |
| openai.gpt-image-1 | GPT Image 1 | OpenAI |
| openai.o1 | o1 | OpenAI |
| openai.o1-mini | o1-mini | OpenAI |
| openai.o3 | o3 | OpenAI |
| openai.o3-mini | o3-mini | OpenAI |
| openai.o4-mini | o4-mini | OpenAI |
| openai.text-embedding-3-large | text-embedding-3-large | OpenAI |
| openai.text-embedding-3-small | text-embedding-3-small | OpenAI |
| openai.text-embedding-ada-002 | text-embedding-ada-002 | OpenAI |
| openai.tts-1 | TTS-1 | OpenAI |
| openai.tts-1-hd | TTS-1 HD | OpenAI |
| openai.whisper-1 | Whisper | OpenAI |
| stackit.cortecs-llama-3-3-70b-instruct-fp8-dynamic | Llama 3.3 70B | STACKIT |
| stackit.google-gemma-3-27b-it | Gemma 3 27B | STACKIT |
| stackit.intfloat-e5-mistral-7b-instruct | E5 Mistral 7B | STACKIT |
| stackit.openai-gpt-oss-120b | GPT-OSS 120B | STACKIT |
| stackit.openai-gpt-oss-20b | GPT-OSS 20B | STACKIT |
| stackit.qwen-qwen3-vl-235b-a22b-instruct-fp8 | Qwen3-VL 235B | STACKIT |
| stackit.qwen-qwen3-vl-embedding-8b | Qwen3 Vision-Language Embedding | STACKIT |