Provider: Azure OpenAI

Call Azure OpenAI models through Respan Gateway with unified logs, cost, and latency.

Use Respan Gateway to call Azure OpenAI deployments (azure/gpt-5.6-sol, azure/gpt-5.6-luna, and azure/gpt-5.6-terra) while keeping unified observability (logs, cost, latency, reliability) in Respan.

Paste this into your coding agent:

Help me set up the Respan gateway to call Azure OpenAI models.
Follow https://www.respan.ai/docs/integrations/gateway/model-providers/azure.md

Quick setup

Send your first request

After configuring your Azure OpenAI 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 examples use azure/gpt-5.6-sol, a live catalog model. Your Azure resource must have a matching deployment. If you use a custom deployment name, configure it in Respan and substitute your deployment model ID.

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/gpt-5.6-sol",
    messages=[{"role": "user", "content": "Hello, Azure OpenAI!"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RESPAN_API_KEY,
  baseURL: "https://api.respan.ai/api",
});

const response = await client.chat.completions.create({
  model: "azure/gpt-5.6-sol",
  messages: [{ role: "user", content: "Hello, Azure OpenAI!" }],
});
console.log(response.choices[0].message.content);

import { createOpenAI } from "@ai-sdk/openai";
import { generateText } from "ai";

const respan = createOpenAI({
  apiKey: process.env.RESPAN_API_KEY!,
  baseURL: "https://api.respan.ai/api",
});

const result = await generateText({
  model: respan.chat("azure/gpt-5.6-sol"),
  prompt: "Hello, Azure OpenAI!",
});
console.log(result.text);

import requests

response = requests.post(
    "https://api.respan.ai/api/chat/completions",
    headers={
        "Authorization": "Bearer YOUR_RESPAN_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "azure/gpt-5.6-sol",
        "messages": [{"role": "user", "content": "Hello, Azure OpenAI!"}],
    },
)
print(response.json()["choices"][0]["message"]["content"])

const response = await fetch("https://api.respan.ai/api/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.RESPAN_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "azure/gpt-5.6-sol",
    messages: [{ role: "user", content: "Hello, Azure OpenAI!" }],
  }),
});

const data = await response.json();
console.log(data.choices[0].message.content);

More integrations

Azure OpenAI models work with every Respan gateway integration:

• OpenAI SDK
• OpenAI Agents SDK
• LangChain
• LangGraph
• LlamaIndex
• Pydantic AI
• Respan native (OTel)

Switch models

Change the model parameter to call any supported model through the same client. Use the azure/ prefix plus your Azure deployment name (or model ID) to disambiguate when routing across providers. Browse the full list on the Models page .

client.chat.completions.create(model="azure/gpt-5.6-sol", messages=messages)
client.chat.completions.create(model="azure/gpt-5.6-luna", messages=messages)
client.chat.completions.create(model="azure/gpt-5.6-terra", 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 OpenAI key (BYOK)

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

{
  "customer_credentials": {
    "azure_openai": {
      "api_key": "YOUR_AZURE_OPENAI_API_KEY",
      "api_base": "https://your-resource.openai.azure.com/",
      "api_version": "2024-10-21"
    }
  }
}

Override credentials per model (Optional)

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

{
  "customer_credentials": {
    "azure_openai": {
      "api_key": "YOUR_AZURE_OPENAI_API_KEY",
      "api_base": "https://your-resource.openai.azure.com/",
      "api_version": "2024-10-21"
    }
  },
  "credential_override": {
    "azure/gpt-5.6-sol": {
      "api_key": "ANOTHER_API_KEY",
      "api_base": "https://another-resource.openai.azure.com/",
      "api_version": "2024-10-21"
    }
  }
}

Log without proxying (Optional)

Already calling Azure OpenAI 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/gpt-5.6-sol",
        "prompt_messages": [{"role": "user", "content": "Hello, how are you?"}],
        "completion_message": {"role": "assistant", "content": "Hello from Azure OpenAI through Respan."},
        "cost": 0.001,
        "generation_time": 1.2,
        "customer_params": {"customer_identifier": "user_123"},
    },
)

See the logging guide for the full setup.