Skip to content
AI Foundation Services LLM serving AI Foundation Services API Key

Models Comparison

Side-by-side comparison of every model currently available on AI Foundation Services. Use the filter chips above the table to narrow by category, provider, cloud, modality, or plan.

Category
Provider
Cloud
Input
Output
Streaming output
Tool calling
Plans
Showing 39 of 39 models
Token-by-token output via Server-Sent Events. Suitable for low-latency, real-time UI. Function / tool calling (OpenAI-compatible). The model can return structured tool invocations. Accepted values of the reasoning_effort parameter, from the platform model datasheet. "-": no values are published for this model. See the Reasoning Control guide. Where the response reports the number of reasoning tokens in the usage object: completion_tokens_details.reasoning_tokens, usage.reasoning_tokens, or not reported (the model reasons, but the response carries no count). "-": the model has no reasoning. Price per million prompt tokens served from the prefix cache: 15% of the normal input price. T-Cloud-hosted models only — cached pricing for external providers will be added later.
BGE-M3 Embedding Other Independent maker Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text Vector ✗ ✗ 8K - - €0.05 €0.05 €0.0075 EssentialProfessionalAgentic
d3 LLM, Vision Other Independent maker Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text, Image Text ✗ ✗ — - - — — — Test
DeepSeek V4.1 Flash LLM, Vision DeepSeek DeepSeek Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text, Image Text ✓ ✓ 1M - - — — — Test
DiffusionGemma 26B A4B LLM, Vision Google Gemma Google Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text, Image Text ✓ ✓ 256K - - — — — Test
Gemma 4 LLM, Vision Google Gemma Google Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text, Image Text ✓ ✓ 102,400 lowmediumhigh completion_tokens_details.reasoning_tokens €0.60 €1.20 €0.09 EssentialProfessionalAgentic
GLM 5.3 LLM, Coding Zhipu AI Zhipu AI Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text Text ✓ ✓ 1M - - €1.40 €4.40 €0.21 EssentialProfessionalAgentic
GLM 5.3 Flash LLM, Coding, Vision Zhipu AI Zhipu AI Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text, Image Text ✓ ✓ 1M lowhighmax usage.reasoning_tokens €0.20 €0.60 €0.03 EssentialProfessionalAgentic
GPT-OSS 120B LLM OpenAI OpenAI Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text Text ✓ ✓ 128K lowmediumhigh not reported €0.20 €0.65 €0.03 EssentialProfessionalAgentic
Jina Embeddings v2 Base DE Embedding Other Independent maker Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text Vector ✗ ✗ 8K - - €0.05 €0.05 €0.0075 EssentialProfessionalAgentic
LightOnOCR-3-4B Vision Other Independent maker Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Image Text ✓ ✗ 32K - - €0.20 €0.60 €0.03 EssentialProfessionalAgentic
Mistral Small 4 LLM, Vision Mistral Mistral AI Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text, Image Text ✓ ✓ 256K nonehigh not reported €0.60 €1.20 €0.09 EssentialProfessionalAgentic
NVIDIA Nemotron 3 Super 120B FP8 LLM Other Independent maker Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text Text ✓ ✓ 1M - not reported €0.60 €1.20 €0.09 EssentialProfessionalAgentic
PaddleOCR-VL-1.6 Vision Other Independent maker Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Image Text ✓ ✗ 128K - - €0.10 €0.40 €0.015 EssentialProfessionalAgentic
Qwen 3.6 35B FP8 LLM, Vision Alibaba Cloud Alibaba Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text, Image Text ✓ ✓ 256K nonelowmediumhigh usage.reasoning_tokens €0.60 €1.20 €0.09 EssentialProfessionalAgentic
Qwen 3.8 27B FP8 LLM, Coding, Vision Alibaba Cloud Alibaba Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text, Image Text ✓ ✓ 256K nonelowmediumxhigh completion_tokens_details.reasoning_tokens €0.50 €2.50 €0.075 EssentialProfessionalAgentic
Qwen3 Embedding 8B Embedding Alibaba Cloud Alibaba Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text Vector ✗ ✗ 32K - - €0.10 €0.10 €0.015 EssentialProfessionalAgentic
Qwen3-Reranker-4B Embedding Alibaba Cloud Alibaba Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Text Score ✗ ✗ 40K - - €0.05 €0.05 €0.0075 EssentialProfessionalAgentic
Whisper Large v3 Audio OpenAI OpenAI Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Audio Text ✗ ✗ 448 - - €14.61 €14.61 €2.1915 EssentialProfessionalAgentic
Whisper Large v3 Turbo Audio OpenAI OpenAI Hosted on T-Cloud Public — Telekom's sovereign infrastructure in Germany. Audio Text ✗ ✗ 448 - - €9.21 €9.21 €1.3815 EssentialProfessionalAgentic
Ada Text Embedding Embedding OpenAI OpenAI Hosted on Microsoft Azure (EU regions). Text Vector ✗ ✗ 8K - - €0.11 €0.11 n/a EssentialProfessionalAgentic
GPT Image 2 Vision, Image Generation OpenAI OpenAI Hosted on Microsoft Azure (EU regions). Text, Image Image ✓ ✗ 4K - - €4.39 €26.33 n/a EssentialProfessionalAgentic
GPT-5.6 Sol LLM OpenAI OpenAI Hosted on Microsoft Azure (EU regions). Text Text ✓ ✓ 1050K nonelowmediumhighxhigh completion_tokens_details.reasoning_tokens €4.50 €27.00 n/a EssentialProfessionalAgentic
GPT-5.6 Terra LLM OpenAI OpenAI Hosted on Microsoft Azure (EU regions). Text Text ✓ ✓ 1050K nonelowmediumhighxhigh completion_tokens_details.reasoning_tokens €3.52 €15.82 n/a EssentialProfessionalAgentic
GPT-6 Astra (>272k) LLM OpenAI OpenAI Hosted on Microsoft Azure (EU regions). Text Text ✓ ✓ 1050K - - €19.36 €72.60 n/a ProfessionalAgentic
GPT-6 Astra (≤272k) LLM OpenAI OpenAI Hosted on Microsoft Azure (EU regions). Text Text ✓ ✓ 272K - - €9.68 €48.40 n/a ProfessionalAgentic
GPT-6 Luna (>272k) LLM OpenAI OpenAI Hosted on Microsoft Azure (EU regions). Text Text ✓ ✓ — nonelowmediumhighxhigh completion_tokens_details.reasoning_tokens €0.22 €0.81 n/a EssentialProfessionalAgentic
GPT-6 Luna (≤272k) LLM OpenAI OpenAI Hosted on Microsoft Azure (EU regions). Text Text ✓ ✓ 272K nonelowmediumhighxhigh completion_tokens_details.reasoning_tokens €0.11 €0.54 n/a EssentialProfessionalAgentic
GPT-6.1 Sol (>272k) LLM OpenAI OpenAI Hosted on Microsoft Azure (EU regions). Text Text ✓ ✓ 1050K lowmediumhighxhigh completion_tokens_details.reasoning_tokens €4.28 €16.02 n/a EssentialProfessionalAgentic
GPT-6.1 Sol (≤272k) LLM OpenAI OpenAI Hosted on Microsoft Azure (EU regions). Text Text ✓ ✓ 272K lowmediumhighxhigh completion_tokens_details.reasoning_tokens €2.14 €10.68 n/a EssentialProfessionalAgentic
Claude Fable 5.1 LLM Anthropic Anthropic Google Cloud Platform & Microsoft Azure Text Text ✓ ✓ 1M - - €9.90 €49.50 n/a ProfessionalAgentic
Claude Haiku 5.5 (>100k) LLM Anthropic Anthropic Google Cloud Platform & Microsoft Azure Text Text ✓ ✓ 1M - - €0.50 €2.48 n/a EssentialProfessionalAgentic
Claude Haiku 5.5 (≤100k) LLM Anthropic Anthropic Google Cloud Platform & Microsoft Azure Text Text ✓ ✓ 100K - - €0.10 €0.50 n/a EssentialProfessionalAgentic
Claude Opus 5.5 LLM, Vision Anthropic Anthropic Google Cloud Platform & Microsoft Azure Text, Image Text ✓ ✓ 1M noneminimallowmediumhighxhighmax not reported €3.92 €19.58 n/a ProfessionalAgentic
Claude Sonnet 5.5 LLM, Vision Anthropic Anthropic Google Cloud Platform & Microsoft Azure Text, Image Text ✓ ✓ 1M noneminimallowmediumhighxhighmax not reported €2.97 €14.85 n/a EssentialProfessionalAgentic
Gemini 3 Flash LLM, Vision, Audio Google Google Hosted on Google Cloud Platform (EU regions). Text, Image, Audio Text ✓ ✓ 1M noneminimallowmediumhigh completion_tokens_details.reasoning_tokens €0.45 €2.70 n/a EssentialProfessionalAgentic
Gemini 3 Pro Image Vision, Image Generation Google Google Hosted on Google Cloud Platform (EU regions). Text, Image Image, Text ✗ ✗ 1M - - €1.80 €108.00 n/a EssentialProfessionalAgentic
Gemini 3.5 Flash LLM Google Google Hosted on Google Cloud Platform (EU regions). Text Text ✓ ✓ 1M noneminimallowmediumhigh completion_tokens_details.reasoning_tokens €1.49 €8.91 n/a EssentialProfessionalAgentic
Gemini 3.8 Flash LLM, Vision, Audio Google Google Hosted on Google Cloud Platform (EU regions). Text, Image, Audio Text ✓ ✓ 1M lowmediumhigh completion_tokens_details.reasoning_tokens €0.74 €3.68 n/a EssentialProfessionalAgentic
Gemini 4 Argon LLM Google Google Hosted on Google Cloud Platform (EU regions). Text Text ✓ ✓ 1M - - €3.96 €19.80 n/a EssentialProfessionalAgentic

Understanding Model Categories

Section titled “Understanding Model Categories”
  • Chat & Reasoning (LLMs) — General-purpose text generation, conversational agents, and reasoning. Most accept multilingual input.
  • Coding — Code-tuned models for completion, refactoring, and review. Stronger on programming benchmarks than general LLMs of similar parameter count.
  • Vision — Multimodal models that accept image input alongside text. Use the same Chat Completions endpoint.
  • Embeddings — Convert text to vectors for semantic search, clustering, and RAG.
  • Audio (Speech-to-Text) — Whisper-family models for transcription and translation.
  • Image Generation — Generate images from text prompts (and optionally an input image).

For sovereignty and data-handling details, see Enterprise Trust.