notewise supports a wide range of LLM providers via LiteLLM. You can use any model LiteLLM supports by setting the --model flag or the DEFAULT_MODEL config key.
gemini/gemini-2.5-flash
openai/gpt-4o
anthropic/claude-3-5-sonnet-20241022
groq/llama3-70b-8192
gpt-4o # routes to OpenAI
claude-3-5-sonnet-20241022 # routes to Anthropic
Supported providers
| Provider | Config Key | Default Model |
|---|
| Google Gemini | GEMINI_API_KEY | gemini/gemini-2.5-flash |
| OpenAI | OPENAI_API_KEY | openai/gpt-4o |
| Anthropic | ANTHROPIC_API_KEY | anthropic/claude-3-5-sonnet-20241022 |
| Groq | GROQ_API_KEY | groq/llama3-70b-8192 |
| xAI | XAI_API_KEY | xai/grok-4 |
| Mistral | MISTRAL_API_KEY | mistral/mistral-large-latest |
| Cohere | COHERE_API_KEY | cohere/command-r-plus |
| DeepSeek | DEEPSEEK_API_KEY | deepseek/deepseek-chat |
Gemini is the default provider — no billing required to start. Get your free API key at AI Studio.
Provider routing
If the model string contains /, the prefix before the slash is the provider. Otherwise, heuristics based on model name prefixes are used.
| Model Prefix | Provider | Required Env Var |
|---|
gemini/* | Google Gemini | GEMINI_API_KEY |
vertex/*, vertex_ai/* | Google Vertex | GEMINI_API_KEY |
openai/*, gpt*, o1*, o3*, o4* | OpenAI | OPENAI_API_KEY |
anthropic/*, claude* | Anthropic | ANTHROPIC_API_KEY |
groq/* | Groq | GROQ_API_KEY |
xai/*, grok* | xAI | XAI_API_KEY |
mistral/* | Mistral | MISTRAL_API_KEY |
cohere/*, command* | Cohere | COHERE_API_KEY |
deepseek/* | DeepSeek | DEEPSEEK_API_KEY |
Unsupported gateway prefixes (azure, openrouter, vercel_ai_gateway) return None for the API key — these are not natively supported and must be configured via environment variables separately.
Quickstart: Changing the default model
Edit ~/.notewise/config.env:
DEFAULT_MODEL=gpt-4o
OPENAI_API_KEY=sk-...
notewise process "URL" --model gpt-4o
Usage tracking
After each video, notewise records token usage and estimated cost in SQLite.
notewise stats # all-time totals
notewise stats --model gemini/gemini-2.5-flash # filter by model
notewise stats --since 7d # last 7 days
completion_cost() and are approximate.
