Generative AI Models by Region
This page provides a list of regions where OCI Generative AI models are available. Select each model for its details.
For on-demand access from a region with no local model processing, use a routing profile to select a supported model and one or more target OCI regions. The tables on this page show model availability in the target OCI regions. Choose a model and region combination that supports on-demand mode.
Each region in the table has one of the following symbols:
| Symbol | Description |
|---|---|
| ✓ | available (on-demand & dedicated AI clusters) |
| ✓o | on-demand only |
| ✓d | dedicated AI clusters only |
| ✓G | available through Oracle Interconnect for Google Cloud only |
| - | not available |
North America (NA)
South America (SA)
| Model Name | Brazil East (Sao Paulo) (OC1) |
Notes |
|---|---|---|
| Cohere Command A Reasoning | ✓d | - |
| Cohere Command A Vision | ✓d | - |
| Cohere Command A | ✓ | - |
| Cohere Embed 4 | ✓d | - |
| Cohere Embed English Image 3 | ✓d | - |
| Cohere Embed English Light Image 3 | ✓d | - |
| Cohere Embed Multilingual Image 3 | ✓d | - |
| Cohere Embed Multilingual Light Image 3 | ✓d | - |
| Cohere Embed English 3 | ✓ | - |
| Cohere Embed English Light 3 | - | - |
| Cohere Embed Multilingual 3 | ✓ | - |
| Cohere Embed Multilingual Light 3 | - | - |
| Cohere Rerank 4.0 (Pro) | ✓d | - |
| Cohere Rerank 4.0 (Fast) | ✓ | - |
| Cohere Rerank 3.5 | ✓ | - |
| Google Gemini 2.5 Pro | - | - |
| Google Gemini 2.5 Flash | ✓o | See External Calls. |
| Google Gemini 2.5 Flash-Lite | - | - |
| Meta Llama 4 Maverick | ✓d | - |
| Meta Llama 4 Scout | ✓d | - |
| Meta Llama 3.3 70B (Standard) | ✓ | - |
| Meta Llama 3.3 70B (Dynamic FP8) | - | - |
| OpenAI gpt-oss-120b | ✓d | - |
| OpenAI gpt-oss-20b | ✓d | - |
| xAI Grok 4.7 | - | - |
| xAI Grok 4.6 | - | - |
| xAI Grok 4.3 | - | - |
| xAI Grok 4.20 Multi-Agent | - | - |
| xAI Grok 4.20 | - | - |
| xAI Voice (Text to Speech) | ✓o | See External Calls. |
Europe (EU)
Middle East (ME)
Asia Pacific (AP)
From regions such as Australia East (Sydney), you can access supported on-demand models through routing profiles. For routing and processing examples, see Where Are Requests Processed?.
Notes for External Calls
Google Models
If you use a routing profile, apply the following notes to the model and target OCI region that serves the request. This can differ from the region where you create or call the profile. Each note describes Google's routing and machine learning processing locations. For examples, see Where Are Requests Processed?.
External Calls to Google Gemini 2.5 Pro for US Regions
The Google Gemini 2.5 Pro model that can be accessed through the OCI Generative AI service in US regions, are hosted externally by Google. Therefore, a call to a Google Gemini 2.5 Pro model (through the OCI Generative AI service) results in a call to a Google location. For Google Gemini 2.5 Pro, a Google Americas regional location is used, which routes the request to only a Google Americas location. Machine Learning Processing takes place within a Google Americas location.
External Calls to Google Gemini 2.5 Pro for EU Regions
The Google Gemini 2.5 Pro model that can be accessed through the OCI Generative AI service in the Frankfurt region, are hosted externally by Google. Therefore, a call to a Google Gemini 2.5 Pro model (through the OCI Generative AI service) results in a call to a Google location. For Gemini 2.5 Pro, a Google European Union (EU) regional location is used, which routes the request to only a Google EU location. Machine Learning Processing takes place within a Google EU location.
External Calls to Google Gemini 2.5 Pro for AP Regions
The Google Gemini 2.5 Pro model that can be accessed through the OCI Generative AI service in the Osaka region, are hosted externally by Google. Therefore, a call to a Google Gemini 2.5 Pro model (through the OCI Generative AI service) results in a call to a Google location. For Gemini 2.5 Pro, a Google Asia Pacific regional location is used, which routes the request to only a Google Asia Pacific location. Machine Learning Processing can take place within any Google location globally.
External Calls to Gemini 2.5 Flash for US Regions
The Gemini 2.5 Flash model that can be accessed through the OCI Generative AI service in US regions, are hosted externally by Google. Therefore, a call to a Gemini 2.5 Flash model (through the OCI Generative AI service) results in a call to a Google location. For Gemini 2.5 Flash, a Google Americas regional location is used, which routes the request to only a Google Americas location. Machine Learning Processing takes place within a Google Americas location.
External Calls to Gemini 2.5 Flash in the Brazil Region
The Gemini 2.5 Flash model that can be accessed through the OCI Generative AI service in the Brazil location is hosted externally by Google. Therefore, a call to a Gemini 2.5 Flash model through the OCI Generative AI service results in a call to a Google location in Brazil. Machine Learning Processing takes place only within Google's Brazil location.
External Calls to Gemini 2.5 Flash for EU Regions
The Gemini 2.5 Flash model that can be accessed through the OCI Generative AI service in the Frankfurt region, are hosted externally by Google. Therefore, a call to a Gemini 2.5 Flash model (through the OCI Generative AI service) results in a call to a Google location. For Gemini 2.5 Flash, a Google European Union (EU) regional location is used, which routes the request to only a Google EU location. Machine Learning Processing takes place within a Google EU location.
External Calls to Gemini 2.5 Flash for AP Regions
The Gemini 2.5 Flash model that can be accessed through the OCI Generative AI service in the Osaka region and the Hyderabad region, are hosted externally by Google. Therefore, a call to a Gemini 2.5 Flash model (through the OCI Generative AI service) results in a call to a Google location. For Gemini 2.5 Flash, a Google Asia Pacific regional location is used, which routes the request to only a Google Asia Pacific location. Machine Learning Processing can take place within any Google location globally.
External Calls to Gemini 2.5 Flash-Lite for US Regions
The Gemini 2.5 Flash-Lite model that can be accessed through the OCI Generative AI service in US regions, are hosted externally by Google. Therefore, a call to a Gemini 2.5 Flash-Lite model (through the OCI Generative AI service) results in a call to a Google location. For Gemini 2.5 Flash-Lite, a Google Americas regional location is used, which routes the request to only a Google Americas location. Machine Learning Processing takes place within a Google Americas location.
External Calls to Gemini 2.5 Flash-Lite for EU Regions
The Gemini 2.5 Flash-Lite model that can be accessed through the OCI Generative AI service in the Frankfurt region, are hosted externally by Google. Therefore, a call to a Gemini 2.5 Flash-Lite model (through the OCI Generative AI service) results in a call to a Google location. For Gemini 2.5 Pro, a Google European Union (EU) regional location is used, which routes the request to only a Google EU location. Machine Learning Processing takes place within a Google EU location.
xAI models
External Calls to xAI Grok Models
The xAI Grok models that can be accessed through the OCI Generative AI service in an OCI region are hosted externally by xAI. Therefore, a call to an xAI Grok model through the OCI Generative AI service results in a call to an xAI location.