All models

QwenAlibaba CloudOpen weights

Qwen 3.8 27B.

Qwen 3.8 27B is the open, dense vision-language model of the Qwen series with 27 billion parameters and optional thinking. It suits code, research, professional workflows, multimodal interaction and long-running agent tasks.

Get started → Providers and prices

base_url="https://api.noirdoc.de/v1" model="qwen/qwen3.8-27b-low"

  • Data centres in Germany
  • § 203 confidentiality
  • Zero retention
  • List prices

Details.

Where the model runs, which rules apply and what it can do.

  1. Data centres in Germany weber.cloud · AKI.IO Contracting party: weber.digital GmbH · based in Balingen, GermanyContracting party: AKI.IO GmbH · based in Berlin, Germany
§ 203 German Criminal Code (StGB)
Confidentiality agreed with weber.cloud and AKI.IO
Weights
Open weights
Features
Tools, Vision, Reasoning and JSON
See how this looks in your account →
Map: Qwen 3.8 27B runs in data centres in Germany (weber.cloud, AKI.IO).

Providers.

We offer Qwen 3.8 27B through these providers.

Provider § 203 model=
€ · 1M tokens Input Cache Read Cache Write Output
weber.cloud DE Own data centres in Germany
§ 203 agreed
qwen/qwen3.8-27b-low Low
Input 0.30 Cache Read 0.09 Output 1.90
weber.cloud DE Own data centres in Germany
§ 203 agreed
qwen/qwen3.8-27b-medium Medium
Input 0.30 Cache Read 0.09 Output 1.90
weber.cloud DE Own data centres in Germany
§ 203 agreed
qwen/qwen3.8-27b-no-thinking No Thinking
Input 0.30 Cache Read 0.09 Output 1.90
weber.cloud DE Own data centres in Germany
§ 203 agreed
qwen/qwen3.8-27b-xhigh XHigh
Input 0.30 Cache Read 0.09 Output 1.90
AKI.IO DE German data centres
§ 203 agreed
Qwen/Qwen3.8-27B
Input 0.15 Cache Read 0.10 Output 0.65

More models.

Alibaba Cloud's Qwen series covers open models for chat, reasoning, code, vision and embeddings in many sizes.

All Qwen models →
Model
€ · 1M tokens Input Cache Read Cache Write Output
Qwen 3.6 35B A3B Tools Vision Reasoning JSON Efficient Qwen MoE — strong in multilingual work and reasoning at low cost. AKI.IO Logo AKI.IO · DE
Input 0.15 Output 0.50
Qwen 3.5 397B A17B Tools Vision Reasoning JSON Large Qwen MoE with 397B parameters, 17B of them active — for code, agents and image and video understanding. IONOS Logo IONOS · DE
Input 0.60 Output 3.60
Qwen 3.5 9B Tools Vision Reasoning JSON Compact multimodal Qwen model with 9B parameters — an efficient architecture for reasoning, code and image understanding. Regolo Logo Regolo · EU
Input 0.10 Output 0.20
Qwen3-Coder-Next Code Tools JSON Specialised code model for generation, refactoring and agentic dev workflows. IONOS Logo IONOS · DE
Input 0.15 Output 0.80
Qwen3-VL Embedding 8B Embeddings Large multimodal embedding model for demanding search and RAG applications. IONOS Logo IONOS · DE
0.11 € per 1M tokens
Qwen3-VL Reranker 8B Reranking Reranker for more precise hits in RAG pipelines — reorders search results. IONOS Logo IONOS · DE
0.045 € per 1M tokens

Get started.

Test selected models right away with €5 starter credit — every model from the first top-up. If you have questions first, talk to our sales team.

Sign in →
python · openai sdk api.noirdoc.de/v1 
import os
from openai import OpenAI

client = OpenAI(
    # one line, that's all
    base_url="https://api.noirdoc.de/v1",
    api_key=os.environ["NOIRDOC_API_KEY"],
)

response = client.chat.completions.create(
    model="qwen/qwen3.8-27b-low",  # provider & model
    messages=[{"role": "user", "content": "Hello"}],
)