AI provider
- Arya managed (default)
- BYOK (Bring Your Own Key)
- Private deployment (Enterprise)
Arya manages everything: infrastructure, providers (mix of Anthropic Claude, OpenAI GPT, Google Gemini), automatic routing to best model. Costs included in credits.
Configure BYOK
Parameters
Temperature
Temperature
0 = deterministic, 1 = creative. Default 0.3 (balanced).
- Low for structured data, classifications
- High for brainstorming, creativity
Max tokens
Max tokens
Max output length. Default 2000.
Reasoning level (compatible models only)
Reasoning level (compatible models only)
How much “thinking” before responding. High = more accurate but slower and more expensive.
Verbose mode
Verbose mode
Shows step-by-step reasoning. Useful for debugging, superfluous for normal use.
Cost limits
To avoid unexpected consumption:Activatable AI features
Pick what Arya can do with AI:AryaChat
Conversational chat.
Document generation
Emails, contracts, quotes.
Call intelligence
Transcription + call summary.
Report chat
Natural language data analysis.
Data enrichment
Company and contact enrichment.
Receipt OCR
Expense reports from photos.
Auto-tagging
Automatic record classification.
Smart suggestions
Proactive suggestions (next-best-action).
AI privacy
- Arya managed: GDPR compliant, no use for global model training
- BYOK OpenAI/Anthropic: subject to provider policies. Verify zero-retention if you have sensitive data.
- Private deployment: data never leaves your infrastructure.
Monitor usage
Dashboard Settings → AI → Analytics:- Consumption per feature
- Consumption per user
- Time trend
- Most expensive queries (for optimisation)
Frequently asked questions
Which provider is best?
Which provider is best?
Depends on use case. Claude excels at long reasoning and analysis. GPT at creativity and code. Arya managed auto-routes to best for each task.
Can I use open-source models (Llama, Mistral)?
Can I use open-source models (Llama, Mistral)?
On Enterprise plans with private deployment, yes. On standard plans, no.