Azure Open AI Model Configuration
- 12 Aug 2025
- 1 Minute to read
- Contributors
- Print
- DarkLight
Azure Open AI Model Configuration
- Updated on 12 Aug 2025
- 1 Minute to read
- Contributors
- Print
- DarkLight
Article summary
Did you find this summary helpful?
Thank you for your feedback!
Connection
To integrate your Unleash self-hosted environment with Azure OpenAI, your instance must be deployed with the models Unleash uses to operate:
Name | Model | Version | Min Recommended Rate Limit |
|---|---|---|---|
gpt4o | gpt-4o | 2024-11-20 | 200K Tokens per Minute |
gpt4o-mini | gpt-4o-mini | 2024-07-18 | 200K Tokens per Minute |
gpt4.1 | gpt-4.1 | 2025-04-14 | 500K Tokens per Minute |
gpt4.1-mini | gpt-4.1-mini | 2025-04-14 | 200K Tokens per Minute |
gpt4.1-nano | gpt-4.1-nano | 2025-04-14 | 200K Tokens per Minute |
gpt5 | gpt-5 | 2025-08-07 | 500K Tokens per Minute |
gpt5-mini | gpt-5-mini | 2025-08-07 | 200K Tokens per Minute |
text-embedding-ada-003 | text-embedding-3-large | 1 | 300K Tokens per Minute |
Regions
To get the best from Unleash we recommend the following regions:
EU Deployment is recommended to be hosted in the
swedencentralregionUS Deployment is recommended to be hosted in the
eastusoreastus2region
Please provide your Unleash representative with the following information:
Instance URL
API Key
Was this article helpful?