next-ai-draw-io/docs/ai-providers.md

AI Provider Configuration

This guide explains how to configure different AI model providers for next-ai-draw-io.

Quick Start

1. Copy .env.example to .env.local
2. Set your API key for your chosen provider
3. Set AI_MODEL to your desired model
4. Run npm run dev

Supported Providers

Google Gemini

GOOGLE_GENERATIVE_AI_API_KEY=your_api_key
AI_MODEL=gemini-2.0-flash

Optional custom endpoint:

GOOGLE_BASE_URL=https://your-custom-endpoint

OpenAI

OPENAI_API_KEY=your_api_key
AI_MODEL=gpt-4o

Optional custom endpoint (for OpenAI-compatible services):

OPENAI_BASE_URL=https://your-custom-endpoint/v1

Anthropic

ANTHROPIC_API_KEY=your_api_key
AI_MODEL=claude-sonnet-4-5-20250514

Optional custom endpoint:

ANTHROPIC_BASE_URL=https://your-custom-endpoint

DeepSeek

DEEPSEEK_API_KEY=your_api_key
AI_MODEL=deepseek-chat

Optional custom endpoint:

DEEPSEEK_BASE_URL=https://your-custom-endpoint

SiliconFlow (OpenAI-compatible)

SILICONFLOW_API_KEY=your_api_key
AI_MODEL=deepseek-ai/DeepSeek-V3  # example; use any SiliconFlow model id

Optional custom endpoint (defaults to the recommended domain):

SILICONFLOW_BASE_URL=https://api.siliconflow.com/v1  # or https://api.siliconflow.cn/v1

Azure OpenAI

AZURE_API_KEY=your_api_key
AZURE_RESOURCE_NAME=your-resource-name  # Required: your Azure resource name
AI_MODEL=your-deployment-name

Or use a custom endpoint instead of resource name:

AZURE_API_KEY=your_api_key
AZURE_BASE_URL=https://your-resource.openai.azure.com  # Alternative to AZURE_RESOURCE_NAME
AI_MODEL=your-deployment-name

Optional reasoning configuration:

AZURE_REASONING_EFFORT=low      # Optional: low, medium, high
AZURE_REASONING_SUMMARY=detailed  # Optional: none, brief, detailed

AWS Bedrock

AWS_REGION=us-west-2
AWS_ACCESS_KEY_ID=your_access_key_id
AWS_SECRET_ACCESS_KEY=your_secret_access_key
AI_MODEL=anthropic.claude-sonnet-4-5-20250514-v1:0

Note: On AWS (Lambda, EC2 with IAM role), credentials are automatically obtained from the IAM role.

OpenRouter

OPENROUTER_API_KEY=your_api_key
AI_MODEL=anthropic/claude-sonnet-4

Optional custom endpoint:

OPENROUTER_BASE_URL=https://your-custom-endpoint

Ollama (Local)

AI_PROVIDER=ollama
AI_MODEL=llama3.2

Optional custom URL:

OLLAMA_BASE_URL=http://localhost:11434

Vercel AI Gateway

Vercel AI Gateway provides unified access to multiple AI providers through a single API key. This simplifies authentication and allows you to switch between providers without managing multiple API keys.

AI_GATEWAY_API_KEY=your_gateway_api_key
AI_MODEL=openai/gpt-4o

Model format uses provider/model syntax:

• openai/gpt-4o - OpenAI GPT-4o
• anthropic/claude-sonnet-4-5 - Anthropic Claude Sonnet 4.5
• google/gemini-2.0-flash - Google Gemini 2.0 Flash

Get your API key from the Vercel AI Gateway dashboard.

Auto-Detection

If you only configure one provider's API key, the system will automatically detect and use that provider. No need to set AI_PROVIDER.

If you configure multiple API keys, you must explicitly set AI_PROVIDER:

AI_PROVIDER=google  # or: openai, anthropic, deepseek, siliconflow, azure, bedrock, openrouter, ollama, gateway

Model Capability Requirements

This task requires exceptionally strong model capabilities, as it involves generating long-form text with strict formatting constraints (draw.io XML).

Recommended models:

• Claude Sonnet 4.5 / Opus 4.5

Note on Ollama: While Ollama is supported as a provider, it's generally not practical for this use case unless you're running high-capability models like DeepSeek R1 or Qwen3-235B locally.

Temperature Setting

You can optionally configure the temperature via environment variable:

TEMPERATURE=0  # More deterministic output (recommended for diagrams)

Important: Leave TEMPERATURE unset for models that don't support temperature settings, such as:

• GPT-5.1 and other reasoning models
• Some specialized models

When unset, the model uses its default behavior.

Recommendations

• Best experience: Use models with vision support (GPT-4o, Claude, Gemini) for image-to-diagram features
• Budget-friendly: DeepSeek offers competitive pricing
• Privacy: Use Ollama for fully local, offline operation (requires powerful hardware)
• Flexibility: OpenRouter provides access to many models through a single API