Azure DeepSeek (gateway)

1
{
2
  "mcpServers": {
3
    "respan-docs": {
4
      "url": "https://mcp.respan.ai/mcp/docs"
5
    }
6
  }
7
}

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

Prerequisites

• A Respan API key
• Azure DeepSeek credentials (BYOK)

Supported SDKs / integrations

Configuration

There are 2 ways to add your Azure DeepSeek credentials to your requests:

Via UI (Global)

1

Navigate to Providers

Go to the Providers page. This page allows you to manage credentials for supported model providers.

2

Add your Azure DeepSeek credentials

Select Azure DeepSeek and add the required credential fields.

• 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

Find credentials in Azure AI Foundry

Open your DeepSeek deployment in Azure AI Foundry and copy the deployment endpoint and API key. Use the OpenAI-compatible base URL for Respan Gateway requests.

4

Configure Load Balancing (Optional)

Add multiple Azure DeepSeek credential sets for redundancy. Use the Load balancing weight field to control traffic distribution.

Via code (Per-Request)

You can pass credentials dynamically in the request body. This is useful if you need to use your users’ own API keys (BYOK).

Add the customer_credentials parameter to your Gateway request:

1
{
2
  "customer_credentials": {
3
    "azure_deepseek": {
4
      "api_key": "YOUR_AZURE_DEEPSEEK_API_KEY",
5
      "api_base": "https://your-resource.openai.azure.com/openai/v1/"
6
    }
7
  }
8
}

Override credentials for a particular model (Optional)

Use credential_override when one request or model should use different credentials than the default provider key.

1
{
2
  "customer_credentials": {
3
    "azure_deepseek": {
4
      "api_key": "YOUR_AZURE_DEEPSEEK_API_KEY",
5
      "api_base": "https://your-resource.openai.azure.com/openai/v1/"
6
    }
7
  },
8
  "credential_override": {
9
    "azure_deepseek/deepseek-chat": {
10
      "api_key": "ANOTHER_AZURE_DEEPSEEK_API_KEY",
11
      "api_base": "https://another-resource.openai.azure.com/openai/v1/"
12
    }
13
  }
14
}

Supported models

Find the complete and current list of Azure DeepSeek model IDs on the Respan Models page. Use the exact model ID shown there in your gateway requests.

Log Azure DeepSeek requests

If you are not using the Gateway to proxy requests, you can still log your Azure DeepSeek requests to Respan asynchronously. This lets you track cost, latency, and performance metrics for external calls.

1
import requests
2
3
url = "https://api.respan.ai/api/request-logs/create/"
4
payload = {
5
  "model": "azure_deepseek/deepseek-chat",
6
  "prompt_messages": [
7
    {
8
      "role": "user",
9
      "content": "Hello, how are you?"
10
    }
11
  ],
12
  "completion_message": {
13
    "role": "assistant",
14
    "content": "Hello from Azure DeepSeek through Respan."
15
  },
16
  "cost": 0.001,
17
  "generation_time": 1.2,
18
  "customer_params": {
19
    "customer_identifier": "user_123"
20
  }
21
}
22
headers = {
23
    "Authorization": "Bearer YOUR_RESPAN_API_KEY",
24
    "Content-Type": "application/json",
25
}
26
27
response = requests.post(url, headers=headers, json=payload)