> ## Documentation Index
> Fetch the complete documentation index at: https://nirmauniversity-d6cdc5d7-dev.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Models and providers

> Choose a LiteLLM provider and set the credentials NoteWise expects.

NoteWise sends generation requests through LiteLLM. Use a model string like `provider/model-name` with `--model` or `DEFAULT_MODEL`.

```bash theme={"theme":{"light":"github-light","dark":"tokyo-night"}}
notewise process "https://youtu.be/VIDEO_ID" --model gemini/gemini-2.5-flash
```

The source default is `gemini/gemini-2.5-flash`.

## Common routes

<CardGroup cols={2}>
  <Card title="Default Gemini path">
    Set `GEMINI_API_KEY` and use `gemini/gemini-2.5-flash`.
  </Card>

  <Card title="OpenAI or Anthropic">
    Set `OPENAI_API_KEY` or `ANTHROPIC_API_KEY`, then use a matching LiteLLM
    model string.
  </Card>

  <Card title="Hosted routing">
    Use OpenRouter, Vercel AI Gateway, Azure, Bedrock, Databricks, Cloudflare,
    Together, Fireworks, or Groq.
  </Card>

  <Card title="Subscription login" href="/config/oauth">
    Use ChatGPT or GitHub Copilot OAuth instead of static API keys.
  </Card>

  <Card title="Custom endpoint" href="/config/configuration#custom-openai-compatible-endpoints">
    Save one or more OpenAI-compatible endpoints with `notewise setup` or
    `notewise inference`.
  </Card>
</CardGroup>

## Credential map

| Provider          | Credential                                        |
| ----------------- | ------------------------------------------------- |
| Gemini / Vertex   | `GEMINI_API_KEY`                                  |
| OpenAI            | `OPENAI_API_KEY`                                  |
| Anthropic         | `ANTHROPIC_API_KEY`                               |
| Groq              | `GROQ_API_KEY`                                    |
| xAI               | `XAI_API_KEY`                                     |
| Mistral           | `MISTRAL_API_KEY`                                 |
| Cohere            | `COHERE_API_KEY`                                  |
| DeepSeek          | `DEEPSEEK_API_KEY`                                |
| OpenRouter        | `OPENROUTER_API_KEY`                              |
| Azure             | `AZURE_API_KEY` or `AZURE_OPENAI_API_KEY`         |
| Vercel AI Gateway | `VERCEL_AI_GATEWAY_API_KEY`                       |
| Together          | `TOGETHERAI_API_KEY`                              |
| Fireworks         | `FIREWORKS_AI_API_KEY`                            |
| Perplexity        | `PERPLEXITYAI_API_KEY`                            |
| Cloudflare        | `CLOUDFLARE_API_KEY` plus `CLOUDFLARE_ACCOUNT_ID` |
| Databricks        | `DATABRICKS_API_KEY` plus `DATABRICKS_API_BASE`   |
| Bedrock           | AWS credential chain                              |
| AI21              | `AI21_API_KEY`                                    |
| Cerebras          | `CEREBRAS_API_KEY`                                |
| DashScope         | `DASHSCOPE_API_KEY`                               |
| DeepInfra         | `DEEPINFRA_API_KEY`                               |
| Hugging Face      | `HUGGINGFACE_API_KEY`                             |
| Jina AI           | `JINA_API_KEY`                                    |
| Novita AI         | `NOVITA_API_KEY`                                  |
| NVIDIA NIM        | `NVIDIA_NIM_API_KEY`                              |
| Replicate         | `REPLICATE_API_KEY`                               |
| SambaNova         | `SAMBANOVA_API_KEY`                               |
| Voyage AI         | `VOYAGE_API_KEY`                                  |

<Warning>
  Never share API keys, OAuth tokens, cookies, raw prompts, or provider
  payloads. Logs and error reports should stay redacted.
</Warning>

## Model inference

When a model string has no explicit provider prefix, NoteWise can infer common key requirements from model names such as Gemini, GPT/OpenAI, Claude, Groq, Grok/xAI, Mistral, Cohere/Command, and DeepSeek.

## Saved custom endpoints

`notewise process --model <name>/<model-id>` automatically resolves a saved
endpoint named `<name>`, uses that profile's base URL and API key, and sends
LiteLLM `openai/<model-id>`. This lookup is exact after endpoint-name
normalization, so profiles remain isolated. Use explicit `--base-url` or
`--api-key` only to override a single run; neither flag changes the saved
profile. When `--base-url` changes a saved endpoint, supply `--api-key` so the
saved credential is never sent to a different origin.

Use `notewise inference list`, `add`, `update`, and `delete` to manage the
saved profiles. See [Configuration](/config/configuration#custom-openai-compatible-endpoints)
for the registry format and setup behavior.