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

# AI Providers

> Configure Workscribe to work with Anthropic, OpenAI, Gemini, Groq, Ollama, or any OpenAI-compatible endpoint.

# AI Providers

Workscribe sends structured event data to your AI provider only when you explicitly run `workscribe summary`. It never sends raw commands, file contents, or file paths — only event categories and metadata.

***

## Anthropic (Claude)

```bash theme={null}
workscribe config set ai.provider anthropic
workscribe config set ai.apiKey sk-ant-...
```

| Setting | Value |
| - | - |
| Default model | `claude-haiku-4-5-20251001` |
| API key required | Yes |

Override the model:

```bash theme={null}
workscribe config set ai.model claude-sonnet-4-6
```

Get an API key at [console.anthropic.com](https://console.anthropic.com).

***

## OpenAI

```bash theme={null}
workscribe config set ai.provider openai
workscribe config set ai.apiKey sk-...
```

| Setting | Value |
| - | - |
| Default model | `gpt-4o-mini` |
| API key required | Yes |

Override the model:

```bash theme={null}
workscribe config set ai.model gpt-4o
```

Get an API key at [platform.openai.com](https://platform.openai.com).

***

## Google Gemini

```bash theme={null}
workscribe config set ai.provider gemini
workscribe config set ai.apiKey AIza...
```

| Setting | Value |
| - | - |
| Default model | `gemini-2.0-flash-lite` |
| API key required | Yes |

Override the model:

```bash theme={null}
workscribe config set ai.model gemini-2.0-flash
```

Get an API key at [aistudio.google.com](https://aistudio.google.com). The API key is sent as a URL query parameter — it does not appear in request headers.

***

## Groq

```bash theme={null}
workscribe config set ai.provider groq
workscribe config set ai.apiKey gsk_...
```

| Setting | Value |
| - | - |
| Default model | `llama-3.1-8b-instant` |
| API key required | Yes |

Override the model:

```bash theme={null}
workscribe config set ai.model llama-3.3-70b-versatile
```

Get an API key at [console.groq.com](https://console.groq.com). Groq's free tier is generous for summary workloads.

***

## Ollama (local)

Run AI summaries entirely on your machine — no API key, no external calls, fully offline.

```bash theme={null}
workscribe config set ai.provider ollama
```

| Setting | Value |
| - | - |
| Default model | `llama3` |
| API key required | No |
| Base URL | `http://localhost:11434` |

**Requirements:**

1. Install Ollama: [ollama.com](https://ollama.com)
2. Pull a model: `ollama pull llama3`
3. Start Ollama: `ollama serve`

Override the model:

```bash theme={null}
workscribe config set ai.model mistral
```

***

## OpenAI-compatible

Works with any endpoint that implements the OpenAI chat completions API — Together AI, Mistral, and others.

```bash theme={null}
workscribe config set ai.provider openai-compatible
workscribe config set ai.apiKey <your-key>
workscribe config set ai.baseUrl https://api.together.xyz/v1
workscribe config set ai.model meta-llama/Llama-3-8b-chat-hf
```

| Setting | Value |
| - | - |
| Default model | None — set `ai.model` manually |
| API key required | Depends on provider |
| Base URL required | Yes |

***

## Switching providers

Switch at any time — existing summaries are cached in the database and unaffected:

```bash theme={null}
workscribe config set ai.provider ollama
```

***

## Troubleshooting

**"AI provider not configured"**
Run `workscribe config set ai.provider <provider>` and ensure an API key is set if required.

**Ollama: connection refused**
Make sure Ollama is running: `ollama serve`

**Anthropic / OpenAI / Groq: 401 Unauthorized**
Check your API key: `workscribe config get ai.apiKey`

**Gemini: 400 API key not valid**
Ensure the key was created in Google AI Studio (not Google Cloud). Gemini keys start with `AIza`.

**Groq: 429 rate limit**
Groq's free tier has per-minute limits. Wait a moment and retry, or upgrade your Groq plan.

**Summary quality is poor on local models**
Try a larger model: `workscribe config set ai.model llama3:70b`. Local models with fewer than 7B parameters may produce inconsistent output.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.