All models

deepseek/deepseek-v4-flash-vision-exp-think.

deepseek/deepseek-v4-flash-vision-exp-think is available through the Noirdoc gateway.

base_url="https://api.noirdoc.de/v1" model="deepseek/deepseek-v4-flash-vision-exp-think"

  • Data centres in the EU
  • no § 203 agreement
  • Zero retention
  • List prices

Details.

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

§ 203 German Criminal Code (StGB)
No provider of this model has a confidentiality agreement
Features
Tools, Vision, Reasoning and JSON
See how this looks in your account →
Map: deepseek/deepseek-v4-flash-vision-exp-think.

Providers.

We offer deepseek/deepseek-v4-flash-vision-exp-think through these providers.

Provider § 203 model=
€ · 1M tokens Input Cache Read Cache Write Output
Weber Cloud
deepseek/deepseek-v4-flash-vision-exp-think
Input 0.10 Output 0.10

More models.

All models →
Model
€ · 1M tokens Input Cache Read Cache Write Output
Claude Opus 5.5 Tools Vision Reasoning JSON Opus-class Claude model for demanding reasoning — long-running agents, code review and multi-step changes across large codebases. Anthropic (Google Vertex)
Input 4.00 Cache Read 0.50 Cache Write — Output 20.00
Claude Sonnet 5.5 Tools Vision Reasoning JSON Sonnet-class Claude model for well-defined everyday work — features, bug fixes, documents, presentations and spreadsheets. Anthropic (Google Vertex)
Input 1.00 Cache Read — Cache Write — Output 1.00
Gemini 4 Argon Google's flagship of the Gemini 4 generation for long, multi-step tasks such as software engineering, mathematics and agents, with tiered reasoning and 1M tokens of context. Google Vertex Logo Google Vertex · EU
Input 1.00 Cache Read — Cache Write — Output 1.00
Gemini 3.1 Flash Lite Earlier Flash-Lite generation — stable for existing integrations and simple high-volume tasks. Google Vertex Logo Google Vertex · EU
Input 1.00 Cache Read — Cache Write — Output 1.00
Qwen 3.8 27B Tools Vision Reasoning JSON Compact Qwen model with 27B parameters — a balanced generalist for chat, reasoning and tool calls. Weber Cloud
Input 0.10 Cache Read 0.10 Cache Write — Output 0.10
Qwen 3.5 9B Tools Vision Reasoning JSON Compact multimodal Qwen model with 9B parameters — an efficient architecture for reasoning, code and image understanding. IONOS Logo IONOS · DE
Input 0.10 Cache Read — Cache Write — Output 0.15
DeepSeek V4 Flash Tools Vision Reasoning JSON Fast variant of the DeepSeek V4 series — a generalist with strengths in code and analysis. Weber Cloud
Input 0.10 Cache Read — Cache Write — Output 0.10
claude-fable-5 Anthropic (Google Vertex)
Input 1.00 Cache Read 50,000.00 Cache Write — Output 10,000.00
claude-sonnet-5 Anthropic (Google Vertex)
Input 0.50 Cache Read 1,000.00 Cache Write 1,000.00 Output 0.50
deepseek/deepseek-v4-flash-vision-exp-max Tools Vision Reasoning JSON Weber Cloud
Input 0.10 Cache Read — Cache Write — Output 0.10

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.

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="deepseek/deepseek-v4-flash-vision-exp-think",  # provider & model
    messages=[{"role": "user", "content": "Hello"}],
)