Generative AI Dedicated Cluster Shapes by Region
This page provides a list of regions where OCI Generative AI models are available. It also displays the dedicated AI cluster unit shapes for hosting those models in each region. Select each model for its details.
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 |
|
<cluster shape> |
The dedicated AI cluster shape to host the model |
North America (NA)
| Model Name | US East (Ashburn) (OC1) |
US Midwest (Chicago) (OC1) |
US West (Phoenix) (OC1) |
Notes |
|---|---|---|---|---|
| Cohere Command A Reasoning | ✓d LARGE_COHERE_V2_2 |
✓d LARGE_COHERE_V2_2 |
✓d LARGE_COHERE_V2_2 |
- |
| Cohere Command A Vision | ✓d LARGE_COHERE_V3 |
✓
LARGE_COHERE_V3 |
✓d LARGE_COHERE_V3 |
- |
| Cohere Command A | ✓d LARGE_COHERE_V3 |
✓
LARGE_COHERE_V3 |
- | - |
| Cohere Command R (08-2024) | ✓d Small Cohere V2 |
✓
Small Cohere V2 |
- | - |
| Cohere Command R+ (08-2024) | ✓d Large Cohere V2_2 |
✓
Large Cohere V2_2 |
- | - |
| Cohere Command R 16K | - |
✓
Small Cohere V2 |
- | - |
| Cohere Command R+ | - |
✓
Large Cohere V2_2 |
- | - |
| Cohere Embed 4 |
✓
Embed Cohere |
✓
Embed Cohere |
- | - |
| Cohere Embed English Image 3 | ✓d Embed Cohere |
✓d Embed Cohere |
- | - |
| Cohere Embed English Light Image 3 | ✓d Embed Cohere |
✓d Embed Cohere |
- | - |
| Cohere Embed Multilingual Image 3 | ✓d Embed Cohere |
✓
Embed Cohere |
- | - |
| Cohere Embed Multilingual Light Image 3 | ✓d Embed Cohere |
✓d Embed Cohere |
- | - |
| Cohere Embed English 3 | - |
✓
Embed Cohere |
- | - |
| Cohere Embed English Light 3 | - |
✓
Embed Cohere |
- | - |
| Cohere Embed Multilingual 3 | ✓d Embed Cohere |
✓ | ✓ | - |
| Cohere Embed Multilingual Light 3 | - |
✓
Embed Cohere |
- | - |
| Cohere Rerank 3.5 | ✓d RERANK_COHERE |
✓d RERANK_COHERE |
- | - |
| Google Gemini 2.5 Pro | ✓o + G | ✓o | ✓o | See External Calls. |
| Google Gemini 2.5 Flash | ✓o + G | ✓o | ✓o | See External Calls. |
| Google Gemini 2.5 Flash-Lite | ✓o + G | ✓o | ✓o | See External Calls. |
| Meta Llama 4 Maverick | - |
✓
Large Generic 2 |
- | - |
| Meta Llama 4 Scout | - |
✓
Large Generic V2 |
- | - |
| Meta Llama 3.3 70B (Standard) | - |
✓
Large Generic |
- | - |
| Meta Llama 3.3 70B (Dynamic FP8) | - |
✓
Large Generic |
✓
Large Generic |
- |
| Meta Llama 3.2 90B | - |
✓
Large Generic V2 |
- | - |
| Meta Llama 3.2 11B Vision | - | ✓d Small Generic V2 |
- | - |
| Meta Llama 3.1 405B | - |
✓
Large Generic 2 |
- | - |
| Meta Llama 3.1 70B | - |
✓
Large Generic |
- | - |
| Meta Llama 3 70B | - |
✓
Large Generic |
- | - |
| OpenAI gpt-oss-120b | ✓d OAI_H100_X2 |
✓
OAI_A100_80G_X2 OAI_H100_X2 |
✓d OAI_A100_80G_X2 |
- |
| OpenAI gpt-oss-20b | ✓d OAI_A10_X2 OAI_H100_X1 |
✓
OAI_A10_X2 OAI_H100_X1 |
✓d OAI_A100_80G_X1 |
- |
| xAI Grok 4.20 Multi-Agent | ✓o | ✓o | ✓o | See External Calls. |
| xAI Grok 4.20 | ✓o | ✓o | ✓o | See External Calls. |
| xAI Grok Code Fast 1 | ✓o | ✓o | ✓o | See External Calls. |
| xAI Grok 4.1 Fast | ✓o | ✓o | ✓o | See External Calls. |
| xAI Grok 4 Fast | ✓o | ✓o | ✓o | See External Calls. |
| xAI Grok 4 | ✓o | ✓o | ✓o | See External Calls. |
| xAI Grok 3 | ✓o | ✓o | ✓o | See External Calls. |
| xAI Grok 3 Mini | ✓o | ✓o | ✓o | See External Calls. |
| xAI Grok 3 Fast | ✓o | ✓o | ✓o | See External Calls. |
| xAI Grok 3 Mini Fast | ✓o | ✓o | ✓o | See External Calls. |
South America (SA)
Europe (EU)
| Model Name | Germany Central (Frankfurt) (OC1) |
EU Sovereign Central (Frankfurt) (OC19) |
UK South (London) (OC1) |
UK Gov South (London) (OC4) |
Notes |
|---|---|---|---|---|---|
| Cohere Command A Reasoning | ✓d LARGE_COHERE_V2_2 |
- | ✓d LARGE_COHERE_V2_2 |
- | - |
| Cohere Command A Vision |
✓
LARGE_COHERE_V3 |
- | ✓d LARGE_COHERE_V3 |
- | - |
| Cohere Command A |
✓
LARGE_COHERE_V3 |
✓d LARGE_COHERE_V3 |
✓
LARGE_COHERE_V3 |
- | - |
| Cohere Command R (08-2024) |
✓
Small Cohere V2 |
- |
✓
Small Cohere V2 |
- | - |
| Cohere Command R+ (08-2024) |
✓
Large Cohere V2_2 |
- |
✓
Large Cohere V2_2 |
- | - |
| Cohere Command R 16K |
✓
Small Cohere V2 |
- |
✓
Small Cohere V2 |
- | - |
| Cohere Command R+ |
✓
Large Cohere V2_2 |
- |
✓
Large Cohere V2_2 |
- | - |
| Cohere Embed 4 | ✓d Embed Cohere |
- | ✓d Embed Cohere |
- | - |
| Cohere Embed English Image 3 | ✓d Embed Cohere |
- | ✓d Embed Cohere |
- | - |
| Cohere Embed English Light Image 3 | ✓d Embed Cohere |
- | ✓d Embed Cohere |
- | - |
| Cohere Embed Multilingual Image 3 | ✓d Embed Cohere |
- | ✓d Embed Cohere |
- | - |
| Cohere Embed Multilingual Light Image 3 | ✓d Embed Cohere |
- | ✓d Embed Cohere |
- | - |
| Cohere Embed English 3 |
✓
Embed Cohere |
- |
✓
Embed Cohere |
- | - |
| Cohere Embed English Light 3 | - | - | - | - | - |
| Cohere Embed Multilingual 3 |
✓
Embed Cohere |
✓d Embed Cohere |
✓
Embed Cohere |
✓d Embed Cohere |
- |
| Cohere Embed Multilingual Light 3 | - | - | - | - | - |
| Cohere Rerank 3.5 | ✓d RERANK_COHERE |
✓d RERANK_COHERE |
✓d RERANK_COHERE |
✓d RERANK_COHERE |
- |
| Google Gemini 2.5 Pro | ✓o + G | - | - | - | See External Calls. |
| Google Gemini 2.5 Flash | ✓o + G | - | - | - | See External Calls. |
| Google Gemini 2.5 Flash-Lite | ✓o + G | - | - | - | See External Calls. |
| Meta Llama 4 Maverick | - | - | ✓d Large Generic 2 |
- | - |
| Meta Llama 4 Scout | - | - | ✓d Large Generic V2 |
- | - |
| Meta Llama 3.3 70B (Standard) |
✓
Large Generic |
✓d Large Generic |
✓
Large Generic |
✓d Large Generic |
- |
| Meta Llama 3.3 70B (Dynamic FP8) |
✓
Large Generic |
✓
Large Generic |
✓
Large Generic |
✓
Large Generic |
- |
| Meta Llama 3.2 90B | - | - |
✓
Large Generic V2 |
- | - |
| Meta Llama 3.2 11B Vision | - | - | ✓d Small Generic V2 |
✓d Small Generic V2 |
- |
| Meta Llama 3.1 405B | ✓d Large Generic 2 |
- | ✓d Large Generic 2 |
- | - |
| Meta Llama 3.1 70B | - | - |
✓
Large Generic |
- | - |
| Meta Llama 3 70B |
✓
Large Generic |
- |
✓
Large Generic |
- | - |
| OpenAI gpt-oss-120b |
✓
OAI_H100_X2 |
✓d OAI_H100_X2 |
✓d OAI_H100_X2 |
✓d OAI_H100_X2 |
- |
| OpenAI gpt-oss-20b |
✓
OAI_A10_X2 OAI_H100_X1 |
✓d OAI_A10_X2 OAI_H100_X1 |
✓d OAI_H100_X1 |
✓d OAI_H100_X1 |
- |
| xAI Grok 4.20 Multi-Agent | - | - | - | - | - |
| xAI Grok 4.20 | - | - | - | - | - |
| xAI Grok Code Fast 1 | - | - | - | - | - |
| xAI Grok 4.1 Fast | - | - | - | - | - |
| xAI Grok 4 Fast | - | - | - | - | - |
| xAI Grok 4 | - | - | - | - | - |
| xAI Grok 3 | - | - | - | - | - |
| xAI Grok 3 Mini | - | - | - | - | - |
| xAI Grok 3 Fast | - | - | - | - | - |
| xAI Grok 3 Mini Fast | - | - | - | - | - |
Middle East (ME)
Asia Pacific (AP)
| Model Name | India South (Hyderabad) (OC1) |
Japan Central (Osaka) (OC1) |
Notes |
|---|---|---|---|
| Cohere Command A Reasoning | ✓d LARGE_COHERE_V2_2 |
✓d LARGE_COHERE_V2_2 |
- |
| Cohere Command A Vision | ✓d LARGE_COHERE_V3 |
✓d LARGE_COHERE_V3 |
- |
| Cohere Command A |
✓
LARGE_COHERE_V3 |
✓
LARGE_COHERE_V3 |
- |
| Cohere Command R (08-2024) | - |
✓
Small Cohere V2 |
- |
| Cohere Command R+ (08-2024) | - |
✓
Large Cohere V2_2 |
- |
| Cohere Command R 16K | - | ✓d Small Cohere V2 |
- |
| Cohere Command R+ (Retired) | - | - | - |
| Cohere Embed 4 | ✓d Embed Cohere |
✓
Embed Cohere |
- |
| Cohere Embed English Image 3 | - | ✓d Embed Cohere |
- |
| Cohere Embed English Light Image 3 | - | ✓d Embed Cohere |
- |
| Cohere Embed Multilingual Image 3 |
✓
Embed Cohere |
✓d Embed Cohere |
- |
| Cohere Embed Multilingual Light Image 3 | - | ✓d Embed Cohere |
- |
| Cohere Embed English 3 | - |
✓
Embed Cohere |
- |
| Cohere Embed English Light 3 | - | - Embed Cohere |
- |
| Cohere Embed Multilingual 3 | - | ✓ | - |
| Cohere Embed Multilingual Light 3 | - | - | - |
| Cohere Rerank 3.5 | - | ✓d RERANK_COHERE |
- |
| Google Gemini 2.5 Pro | - | ✓o | See External Calls. |
| Google Gemini 2.5 Flash | ✓o | ✓o | See External Calls. |
| Google Gemini 2.5 Flash-Lite | - | - | - |
| Meta Llama 4 Maverick | ✓d Large Generic 2 |
✓d Large Generic 2 |
- |
| Meta Llama 4 Scout | ✓d Large Generic V2 |
✓d Large Generic V2 |
- |
| Meta Llama 3.3 70B (Standard) | ✓d Large Generic |
✓
Large Generic |
- |
| Meta Llama 3.3 70B (Dynamic FP8) | ✓d Large Generic |
✓
Large Generic |
- |
| Meta Llama 3.2 90B | - |
✓
Large Generic V2 |
- |
| Meta Llama 3.2 11B Vision | - | ✓d Small Generic V2 |
- |
| Meta Llama 3.1 405B | - | ✓d Large Generic 2 |
- |
| Meta Llama 3.1 70B | - |
✓
Large Generic |
- |
| Meta Llama 3 70B | - | - | - |
| OpenAI gpt-oss-120b | ✓d OAI_H100_X2 |
✓
OAI_H100_X2 |
- |
| OpenAI gpt-oss-20b | ✓d OAI_H100_X1 |
✓
OAI_H100_X1 |
- |
| xAI Grok 4.20 Multi-Agent | - | - | - |
| xAI Grok 4.20 | - | - | - |
| xAI Grok Code Fast 1 | - | - | - |
| xAI Grok 4.1 Fast | - | - | - |
| xAI Grok 4 Fast | - | - | - |
| xAI Grok 4 | - | - | - |
| xAI Grok 3 | - | - | - |
| xAI Grok 3 Mini | - | - | - |
| xAI Grok 3 Fast | - | - | - |
| xAI Grok 3 Mini Fast | - | - | - |
Notes for External Calls
Google Models
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 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 are hosted in an OCI data center, in a tenancy provisioned for xAI. The xAI Grok models, which can be accessed through the OCI Generative AI service, are managed by xAI.