DeepSeek V3 and R1 inside your own network, on an 8-GPU node, so none of your prompts reach a hosted API.
Pilot $4,900 fixed
$4,900 fixed. V3 and R1 share the same 671B base with 37B parameters active per token. The FP8 weights alone are 689 GB, more than an 8× H100 node holds, so plan for 8× H200 or B200 at FP8, or 8× H100 with a 4-bit build.
72 h$4,900 fixed
DeepSeek V3 / R1 live on your data in 72 hours. The clock starts after access and prerequisites.
/v1OpenAI-compatible
OpenAI-compatible endpoint. Your applications switch by changing the base URL.
Evalon your data
Reference evaluation on your data. Readout and production scoping.
We size the hardware and source it at cost, with no markup. Ballpark: one H100 80GB ≈ $25–30k; a 4×H100 node ≈ $180–240k; smaller models run on far less.
The model is one parameter. Everything else in your application stays as it is.
client = OpenAI(
base_url="https://llm.yourcompany.internal/v1", # inside your network
api_key="your-key",
)
reply = client.chat.completions.create(
model="deepseek-v3-r1",
messages=[{"role": "user", "content": "Summarise this contract."}],
)R1 is released under the MIT licence.
V3 ships under the DeepSeek Model Agreement, which permits commercial use and carries use-based restrictions that pass on to your users.
We read the current text for the release you pick during scoping.
Published by DeepSeek. We are not affiliated with the vendor. This is a summary, not legal advice.
Tell us the model, the data and the GPUs you have. An engineer from Limassol or Auckland scopes the 72-hour pilot with you.