WGRIN Tools · Azure AI models
gpt-4o-mini
gpt-4o-mini (version 2024-07-18) is offered in Sweden Central as DataZoneBatch, DataZoneProvisionedManaged, DataZoneStandard, GlobalBatch, GlobalProvisionedManaged, GlobalStandard, ProvisionedManaged and Standard. Its GlobalStandard token price is not published in the Azure Retail Prices API as of the last refresh.
Versions
| Version | Region | Lifecycle | Default version | Retirement (inference) | Token counting |
|---|---|---|---|---|---|
| 2024-07-18 | Sweden Central | Deprecating | Yes | 2027-04-14 | o200k_base · exact |
Exact for text: the encoding is documented for this model. Token counts never include message framing, tools, images or hidden reasoning tokens.
Availability and where data is processed
Sweden Central (swedencentral)
| Version | Deployment type | Inference processing | Data at rest | First observed |
|---|---|---|---|---|
| 2024-07-18 | Data Zone Batch (DataZoneBatch) | Within the EU data zone (Microsoft's EU Data Boundary, which may include EFTA countries such as Norway and Switzerland), not only in the selected region. | Stays in the resource's geography. | 2026-10-04 |
| 2024-07-18 | Data Zone Provisioned (DataZoneProvisionedManaged) | Within the EU data zone (Microsoft's EU Data Boundary, which may include EFTA countries such as Norway and Switzerland), not only in the selected region. | Stays in the resource's geography. | 2026-10-04 |
| 2024-07-18 | Data Zone Standard (DataZoneStandard) | Within the EU data zone (Microsoft's EU Data Boundary, which may include EFTA countries such as Norway and Switzerland), not only in the selected region. | Stays in the resource's geography. | 2026-10-04 |
| 2024-07-18 | Global Batch (GlobalBatch) | Any Azure region worldwide (Microsoft's global infrastructure). | Stays in the resource's geography. | 2026-10-04 |
| 2024-07-18 | Global Provisioned (GlobalProvisionedManaged) | Any Azure region worldwide (Microsoft's global infrastructure). | Stays in the resource's geography. | 2026-10-04 |
| 2024-07-18 | Global Standard (GlobalStandard) | Any Azure region worldwide (Microsoft's global infrastructure). | Stays in the resource's geography. | 2026-10-04 |
| 2024-07-18 | Regional Provisioned (ProvisionedManaged) | Within the resource's geography. | Stays in the resource's geography. | 2026-10-04 |
| 2024-07-18 | Standard (regional) (Standard) | Within the resource's geography. | Stays in the resource's geography. | 2026-10-04 |
The region is where Microsoft's catalogue lists the model and where you would create your resource. It is not by itself where requests are processed: that depends on the deployment type (Microsoft: deployment types).
Retail token prices
Price not published in the Azure Retail Prices API as of 2026-10-04.
Context window and output limits
| Version | Limit | Tokens | Source |
|---|---|---|---|
| 2024-07-18 | Context window | 128,000 | as listed by Microsoft's model API |
| 2024-07-18 | Max output | 16,384 | as listed by Microsoft's model API |
Capabilities flagged by Microsoft
- Chat completions API yes
- Responses API yes
- Assistants API yes
- Agents yes
- Realtime API —
- Audio —
- Embeddings —
- Image generation —
- Priority processing (deployment types) —
- Flex processing (deployment types) —
As flagged in Microsoft's model API. The flags are incomplete: “—” means not flagged, not “not supported”.
History
- Model added: gpt-4o-mini@swedencentral
History available since 2026-10-04 (first observation by WGRIN). Microsoft's effective date is the start of the current price only; WGRIN has no Microsoft price history before its first observation.