Skip to navigation
ModelsMore providers

Provider: Azure DeepSeek

Call Azure DeepSeek models through Respan Gateway with unified logs, cost, and latency.
This page is for Respan LLM Gateway users.

Use Respan Gateway to call Azure DeepSeek models while keeping unified observability (logs, cost, latency, reliability) in Respan.

Azure DeepSeek requires bring your own key (BYOK). Provider usage cannot be paid with Respan credits.

Quick setup

1

Get a Respan API key

Sign up and create a key on the API keys page.

2

Add your Azure DeepSeek credentials

Configure your Azure DeepSeek credentials on the Providers page before using the examples below. See Use your own Azure DeepSeek key.

Send your first request

After configuring your Azure DeepSeek credentials in Respan, pick the integration that matches your stack. The base URL is https://api.respan.ai/api and your application authenticates with RESPAN_API_KEY.

The recommended path. Point the OpenAI SDK at the Respan gateway and call any Azure DeepSeek model.

from openai import OpenAI
client = OpenAI(
    api_key="YOUR_RESPAN_API_KEY",
    base_url="https://api.respan.ai/api",
)
response = client.chat.completions.create(
    model="azure_deepseek/deepseek-v3.2",
    messages=[{"role": "user", "content": "Hello, Azure DeepSeek!"}],
)
print(response.choices[0].message.content)

More integrations

Azure DeepSeek models work with every Respan gateway integration:

Switch models

Change the model parameter to call any supported model through the same client. Use the azure_deepseek/ prefix to disambiguate when routing across providers. Browse the full list on the Models page.

client.chat.completions.create(model="azure_deepseek/deepseek-v3.2", messages=messages)
client.chat.completions.create(model="azure_deepseek/deepseek-v3.2-speciale", messages=messages)
client.chat.completions.create(model="openai/gpt-6-sol", messages=messages)
client.chat.completions.create(model="anthropic/claude-opus-5-5", messages=messages)

Use your own Azure DeepSeek key (BYOK)

Azure DeepSeek credentials are required. Configure them in Respan or pass them with each request using one of the options below.

1

Open Providers

Go to the Providers page.

2

Add Azure DeepSeek

Select Azure DeepSeek and paste your credentials:

  • azure_deepseek.api_key, your Azure AI Foundry API key
  • azure_deepseek.api_base, your Azure AI Foundry endpoint or Azure OpenAI-compatible base URL
3

Load balancing (Optional)

Add multiple credential sets and use Load balancing weight to distribute traffic across them.

Override credentials per model (Optional)

Use credential_override when one model on a request should use a different Azure deployment than the default.

{
  "customer_credentials": {
    "azure_deepseek": {
      "api_key": "YOUR_AZURE_DEEPSEEK_API_KEY",
      "api_base": "https://your-resource.openai.azure.com/openai/v1/"
    }
  },
  "credential_override": {
    "azure_deepseek/deepseek-v3.2": {
      "api_key": "ANOTHER_AZURE_DEEPSEEK_API_KEY",
      "api_base": "https://another-resource.openai.azure.com/openai/v1/"
    }
  }
}

Log without proxying (Optional)

Already calling Azure DeepSeek directly? Send logs to Respan asynchronously to track cost, latency, and performance for those external calls.

import requests
requests.post(
    "https://api.respan.ai/api/request-logs/create/",
    headers={
        "Authorization": "Bearer YOUR_RESPAN_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "azure_deepseek/deepseek-v3.2",
        "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
        "completion_message": {"role": "assistant", "content": "Hello from Azure DeepSeek through Respan."},
        "cost": 0.001,
        "generation_time": 1.2,
        "customer_params": {"customer_identifier": "user_123"},
    },
)

See the logging guide for the full setup.