Skip to main content
Azure OpenAI Service provides the same OpenAI models through Microsoft’s cloud infrastructure — adding data residency controls, private networking, and enterprise compliance (SOC 2, HIPAA, ISO 27001). Use this provider when your deployment requires regional data handling or Azure-native security.

​
Quick config

"llm_agent": {
  "agent_type": "simple_llm_agent",
  "agent_flow_type": "streaming",
  "llm_config": {
    "provider": "azure-openai",
    "model": "gpt-5.4-mini",
    "max_tokens": 150,
    "temperature": 0.2
  }
}
Connect your Azure account at platform.bolna.ai/auth/azure. You’ll need your Azure endpoint URL, API key, and deployment name.

​
Supported models

ModelContextBest forNotes
gpt-5.51M tokensMaximum quality; complex tasksFlagship; highest cost
gpt-5.41M tokensGeneral-purpose productionStrong reasoning at lower cost than 5.5
gpt-5.4-mini400K tokensMost voice agentsRecommended — best latency/cost balance
gpt-5.4-nano400K tokensUltra-high-volume, simple tasksCheapest option
gpt-4.11M tokensPrevious gen; still availableStable if already deployed
gpt-4.1-mini1M tokensPrevious gen; still availableStable if already deployed
gpt-4o128K tokensPrevious gen; still availableStable if already deployed
gpt-4o-mini128K tokensPrevious gen; still availableStable if already deployed
Azure model availability varies by region. Not all models are available in all Azure regions immediately at launch. Check the Azure OpenAI model availability page for your region.

​
Key settings

SettingTypeRecommendedDescription
providerstring"azure-openai"Provider name
modelstring"gpt-5.4-mini"Model/deployment name
max_tokensinteger150Cap on response length — keep short for voice
temperaturefloat0.2Lower = more consistent; good for scripted calls
agent_flow_typestring"streaming"Always "streaming" for voice

​
When to use Azure OpenAI vs direct OpenAI

Use Azure OpenAI when:
  • Your data must stay within a specific region (EU data residency, HIPAA)
  • You need private networking (VNet, private endpoints)
  • Your organization already uses Azure for infrastructure
  • You need enterprise SLA guarantees
Use direct OpenAI when:
  • Simplest setup is preferred
  • You don’t have compliance requirements for data residency
  • You want access to the latest models as soon as they launch (Azure has a short lag)

​
FAQ

Yes. In Azure OpenAI, you create a named deployment for each model in the Azure portal. The deployment name is what you pass as the model field in Bolna config.
Azure mirrors OpenAI’s lineup but with a short availability lag after new models launch. All GPT-5.x, GPT-4.1, and GPT-4o variants are available. Check Microsoft’s model page for your region.
Use gpt-5.4-mini or gpt-4.1-mini, keep max_tokens at 150, and deploy to an Azure region geographically close to your users. See Latency for more.