Available Models

AI Foundation Services provides access to a wide range of open-source and proprietary LLMs, embedding models, vision models, and audio models — all through a single OpenAI-compatible API.

Featured Models

GPT OSS 120B

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Qwen 3 Next 80B Instruct

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Qwen 3 VL 30B Instruct

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Qwen 3 30B

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Meta LLama 3.3 70B

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Mistral Small 24B Instruct 2501

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Qwen 3 Coder 30B

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Qwen2.5 Coder 32B Instruct

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

GPT 5.2

Cloud: Azure Server Location: Sweden Data Processing: EU

GPT 5

Cloud: Azure Server Location: Sweden Data Processing: EU

GPT 5 Mini

Cloud: Azure Server Location: Sweden Data Processing: EU

o4 Mini

Cloud: Azure Server Location: Sweden Data Processing: EU

o3

Cloud: Azure Server Location: Sweden Data Processing: EU

Claude 4.5 Sonnet

Cloud: GCP Server Location: Europe Data Processing: EU

Claude 4 Sonnet

Cloud: GCP Server Location: Europe Data Processing: EU

Gemini 3 Pro

Cloud: GCP Server Location: Europe Data Processing: EU

Gemini 2.5 Pro

Cloud: GCP Server Location: Europe Data Processing: EU

Gemini 2.5 Flash

Cloud: GCP Server Location: Europe Data Processing: EU

GPT 4.1

Cloud: Azure Server Location: France Data Processing: EU

GPT 4.1 Mini

Cloud: Azure Server Location: France Data Processing: EU

GPT 4o

Cloud: Azure Server Location: France Data Processing: EU

GPT Image 1

Cloud: Azure Server Location: Sweden Data Processing: EU

o3 Mini

Cloud: Azure Server Location: Sweden Data Processing: EU

o1 Mini

Cloud: Azure Server Location: Sweden Data Processing: EU

Claude 3.7 Sonnet

Cloud: GCP Server Location: Europe Data Processing: EU

Embedding BGE M3

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Jina Embeddings v2 Base De

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Jina Embeddings v2 Base Code

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

TSI Col Qwen 2 2b v1.0

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Whisper Large v3

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Whisper Large v3 Turbo

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

Teuken 7B Instruct

Cloud: T-Cloud Server Location: Germany Data Processing: Germany

For a complete list with pricing, see the Plans & Pricing page.

List Models via API

curl "$OPENAI_BASE_URL/models" \
  -H "Authorization: Bearer $OPENAI_API_KEY"

from openai import OpenAI

client = OpenAI()

models = client.models.list()
for model in models.data:
    print(model.id)

import OpenAI from "openai";

const client = new OpenAI();

const models = await client.models.list();
for (const model of models.data) {
  console.log(model.id);
}

Model Metadata

Each model includes metadata you can inspect:

models = client.models.list()
print(models.data[0].meta_data)

{
  "model_type": "LLM",
  "source_type": "OPEN SOURCE",
  "max_sequence_length": 128000,
  "hidden_size": 0,
  "max_output_length": 0,
  "deployment_region": "otc-germany",
  "location": "otc-germany",
  "license": "https://www.llama.com/llama3_3/license/",
  "display_name": "Meta LLama 3.3 70B",
  "deployment_country": "Germany, EU",
  "input_modalities": ["text"],
  "output_modalities": ["text"],
  "model_lifecycle_stage": "Stable",
  "is_externally_hosted": false
}

Key fields:

model_type — LLM, EMBEDDING, STT (audio)
max_sequence_length — Maximum input + output tokens
hidden_size — Embedding vector dimensions (embedding models only)
max_output_length — Maximum output tokens the model can generate
deployment_region — Where the model is hosted (e.g., otc-germany for T-Cloud Germany)

Model Categories

Category	Examples	Use Case
LLM	Llama 3.3 70B, GPT 4.1, Claude Sonnet 4, Qwen 3	Text generation, chat, reasoning
Embedding	jina-embeddings-v2-base-de, text-embedding-bge-m3	Semantic search, RAG
Vision	Qwen3-VL-30B-A3B-Instruct-FP8, Gemini 2.5 Flash	Image analysis, multimodal chat
Audio/STT	whisper-large-v3, whisper-large-v3-turbo	Speech-to-text, translation
Image Generation	gpt-image-1	Image creation from text prompts

Hosting & Compliance

Open-source models are hosted on the T-Cloud in Germany, fully GDPR-compliant.
Proprietary models (GPT, Claude, Gemini) are hosted via MS Azure, AWS, or GCP in GDPR-compliant configurations.

All data processing stays within the EU.