DeepSeek V4 Pro (Azure)

PremiumOpen weights

Azure AI FoundryReasoningdeepseek-v4-pro-azure

DeepSeek V4 Pro hosted on Azure AI Foundry — Global Standard tier, US region. Distinct from the direct `deepseek-v4-pro` route (APAC region, direct DeepSeek): same model, hosted in Microsoft-managed US infrastructure.

DeepSeek V4 Pro on Azure AI Foundry — distinct from the direct `deepseek-v4-pro` route (region APAC, direct DeepSeek): same model, US-hosted on Microsoft-managed infrastructure. Launched 2026-07 (plan 047) after a verified live Foundry completion + same-day pricing confirmation. NOT PHI-eligible on this row — no HIPAA/BAA claim; the model-level PHI eligibility feature is a separate follow-on. The upstream Azure deployment name is operator-configured via the `AZURE_FOUNDRY_DEPLOYMENT` platform setting (a JSON map); the catalog id shown here stays a Conduix-facing id.

Capabilities

ReasoningJSON mode

Recommended for

reasoning
analysis

Using this model through Conduix

Call it by its id, or let a routing alias pick it as part of a governed, cross-provider chain with automatic failover.

Direct model iddeepseek-v4-pro-azure

Not currently part of a routing alias — request it by id.

Get started

Conduix is OpenAI-API-compatible — point any OpenAI SDK at https://api.conduix.ai/v1 and pass deepseek-v4-pro-azure as the model.

from conduix import Conduix

client = Conduix(api_key="cx_live_YOUR_KEY")  # base URL is built in

response = client.chat.completions.create(
    model="deepseek-v4-pro-azure",
    messages=[{"role": "user", "content": "Hello, Conduix!"}],
)
print(response.choices[0].message.content)

Reasoning: Reasons step-by-step — best for hard, multi-step problems.
JSON mode: Set response_format for guaranteed-valid JSON output.

The response's x-conduix-model-served header tells you exactly which model answered. See the quickstart for keys, headers, and usage.