Set up OpenAI, Anthropic, or Ollama providers.
Choose one:
| Field | Description |
|---|---|
| API Endpoint | Full URL or base URL. If the URL doesn't end with /chat/completions, the path /v1/chat/completions is auto-appended. |
| API Key | Provider API key. Optional for Ollama. Stored only in chrome.storage.local, never uploaded. |
| Model | Model name. Leave empty for defaults. |
| System Prompt | Custom system prompt. Leave empty for the default sales outreach prompt. |
| Provider | Default Endpoint |
|---|---|
| OpenAI | https://api.openai.com/v1/chat/completions |
| Anthropic | https://api.anthropic.com/v1/messages |
| Ollama | http://localhost:11434/v1/chat/completions |
| Provider | Default Model |
|---|---|
| OpenAI | gpt-4o-mini |
| Anthropic | claude-3-5-sonnet-latest |
| Ollama | llama3.2 |
max_tokens is set to 8192 for OpenAI-compatible calls, which is sufficient for reasoning models (like DeepSeek-R1) that consume tokens in a separate reasoning field before producing the final answer.
© 2026 Sifted Network. AI-powered Business Development Network.