Models
AI-Starter supports AI models across multiple platforms. Below is the list of models available as official assistants.
Caution
Preview and experimental models may be discontinued without notice at the provider's discretion.
Model Characteristics
The following is based on evaluations within the development team. Each model has different strengths and characteristics.
| Series | Characteristics |
|---|---|
| Claude | Excels in text comprehension and coding capabilities with stable performance |
| Nova | Available at low cost |
| Gemini | Excellent cost-performance and multimodal processing |
| OpenAI | Rich tool ecosystem including web search and image generation |
AWS
Claude
| Model Name | Model ID | Description |
|---|---|---|
| Claude Haiku 4.5 | jp.anthropic.claude-haiku-4-5-20251001-v1:0 | Lightweight and fast model |
| Claude Sonnet 4.6 | jp.anthropic.claude-sonnet-4-6 | Well-balanced in performance and cost |
| Claude Sonnet 4.6 Thinking | jp.anthropic.claude-sonnet-4-6 | Supports reasoning with Adaptive Thinking |
| Claude Sonnet 4.6 Thinking with Tool | jp.anthropic.claude-sonnet-4-6 | Supports reasoning and tool execution |
| Claude Opus 4.6 | global.anthropic.claude-opus-4-6-v1 | The most powerful Claude model |
Nova
| Model Name | Model ID | Description |
|---|---|---|
| Nova Micro | apac.amazon.nova-micro-v1:0 | Lightweight and fast model |
| Nova 2 Lite | jp.amazon.nova-2-lite-v1:0 | Supports file analysis with Code Interpreter |
| Nova 2 Lite with Web Search | us.amazon.nova-2-lite-v1:0 | Supports web search and file analysis |
| Nova Pro | apac.amazon.nova-pro-v1:0 | High-performance Nova model |
| Nova Premier | us.amazon.nova-premier-v1:0 | The most powerful Nova model |
| Nova Canvas | amazon.nova-canvas-v1:0 | Image generation model |
Note
Models with the us. prefix require the US East 1 (N. Virginia) region.
OpenAI
| Model Name | Model ID | Description |
|---|---|---|
| GPT-5.2 | gpt-5.2 | High-performance model with web search |
| GPT-5.2 with Code Interpreter | gpt-5.2 | Supports code execution and file analysis |
| GPT-5.2 Thinking | gpt-5.2 | High-performance model with reasoning |
| GPT-5.2 Chat | gpt-5.2-chat-latest | The latest GPT-5.2 used in ChatGPT |
| GPT-5.2 Codex | gpt-5.2-codex | Optimized for coding tasks |
| GPT-5 Search API | gpt-5-search-api | Specialized for web search |
| GPT Image 1 Mini | gpt-image-1-mini | Image generation model |
| GPT Image 1.5 | gpt-image-1.5 | High-quality image generation model |
Azure
| Model Name | Model ID | Description |
|---|---|---|
| Azure Model Router | model-router | Automatically selects the optimal model per request |
| Azure GPT-5.2 | gpt-5.2 | High-performance model on Azure |
| Azure GPT-5.2 Thinking | gpt-5.2 | High-performance model with reasoning |
| Azure GPT Image 1 Mini | gpt-image-1-mini | Image generation model |
| Azure GPT Image 1.5 | gpt-image-1.5 | High-quality image generation model |
Google
| Model Name | Model ID | Description |
|---|---|---|
| Gemini Flash-Lite Latest | gemini-flash-lite-latest | Lightweight and fast preview model |
| Gemini Flash Latest | gemini-flash-latest | Preview model with reasoning and web search |
| Gemini 3 Flash Preview | gemini-3-flash-preview | Balanced model with reasoning and web search |
| Gemini 3.1 Pro Preview | gemini-3.1-pro-preview | High-performance preview model |
| Gemini 3.1 Pro Thinking | gemini-3.1-pro-preview | High-performance model with reasoning |
| Gemini 2.5 Flash Image | gemini-2.5-flash-image | Generates both text and images |
| Imagen 3 | imagen-3.0-generate-002 | Image generation model |
| Imagen 4 | imagen-4.0-generate-001 | Image generation model (Preview) |
| Imagen 4 Ultra | imagen-4.0-ultra-generate-001 | Highest quality image generation model (Experimental) |
Recommended Models
| Use Case | Recommended Model |
|---|---|
| General Q&A | Claude Sonnet 4.6 |
| Advanced Q&A | Claude Opus 4.6 |
| Creative writing | Claude Sonnet 4.6 |
| Coding | Claude Opus 4.6 / GPT-5.2 Codex |
| Business document assistance | Claude Haiku 4.5 |
| Translation assistance | Claude Haiku 4.5 |
| Long text comprehension | Gemini 2.5 Flash |
| Questions about images | Gemini 3 Flash Preview |
| Questions about text files | Gemini 3 Flash Preview |
| Questions about PDF files | Gemini 3 Flash Preview |
| Questions about spreadsheets | Claude Opus 4.6 |
| Image generation | Gemini 2.5 Flash Image Preview (Nano Banana) / GPT Image 1 Mini |
| Web search | GPT-5.2 Thinking / GPT-5 Search API |
| Just want to try it out | Nova 2 Lite |
Additional Resources
The following external sites are helpful for comparing generative AI models. Note that information is regularly updated, so always verify the latest data and reliability.
Custom Assistants
In addition to the official assistants listed above, administrators can create custom assistants to use any model. See Assistants for details.