Live site → enricopesce.github.io/oci-genai-catalog
A single-page reference cataloguing the active Oracle Cloud Infrastructure (OCI) Generative AI lineup for commercial OCI regions (OC1), verified April 2026.
| Section | Details |
|---|---|
| Chat models | Cohere Command A family · Google Gemini 2.5 · Meta Llama 4 · OpenAI gpt-oss · xAI Grok 4 |
| Embedding models | Cohere Embed v3 & v4 (text + multimodal) |
| Rerank model | Cohere Rerank 3.5 |
| Imported models | 79 community/open-weight models via OCI Model Catalog |
| Selection wizard | Guided 4-step model picker (use case → quality/speed → deployment → region) |
Columns covered: Model ID · Tier · Context window · Multimodal · Tool use · Fine-tuning · Reasoning · Status · Best for
- 5 native providers + 79 imported models across 8 provider families
- Commercial OCI regions (OC1) covered in the UI; sovereign and government regions are not yet modeled
- Dark / Light mode toggle (preference saved in
localStorage) - Guided model selection wizard
- Fully static — no JavaScript framework, no build step
- Mobile responsive
All data sourced from the OCI official documentation.
| Provider | Models |
|---|---|
| Cohere | Command A Reasoning, Command A Vision, Command A, Command R+, Command R, Embed v4/v3, Rerank 3.5 |
| Gemini 2.5 Pro, Flash, Flash-Lite | |
| Meta | Llama 4 Maverick, Llama 4 Scout, Llama 3.3 70B, Llama 3.2 90B/11B Vision, Llama 3.1 405B |
| OpenAI | gpt-oss-120b, gpt-oss-20b |
| xAI | Grok 4, Grok 4 Fast, Grok 4.1 Fast, Grok 4.20, Grok 4.20 Multi-Agent, Grok 3, Grok 3 Fast, Grok 3 Mini, Grok 3 Mini Fast, Grok Code Fast 1 |
| Provider | Models |
|---|---|
| Alibaba | Qwen3, Qwen3-VL, Qwen2.5, QwQ families |
| DeepSeek | DeepSeek-R1-Distill-Qwen-32B |
| Google (Gemma) | Gemma 3 (270M–27B), Gemma 2 (2B–27B) |
| Microsoft | Phi-4, Phi-3 family |
| Mistral | Mixtral 8x7B, Mistral Nemo, Mistral 7B, E5-Mistral |
| NVIDIA | Nemotron Super 120B, Nano 30B, Llama Nemotron 70B |