Building Agents
When building your agent, you can customize every detail to match your organization’s standards, tone, and goals.Enable Citations
Allow citations if you would like your responses to include references to knowledge base sources in its responses.
Models
VIVI supports a range of large language models, each suited to specific use cases. Below is an overview of the current model lineup:| Model | Input (tokens) | Maximum Output (tokens) | Use Case |
|---|---|---|---|
| gpt-5.1-high | 272,000 | 128,000 | Maximum intelligence with deep reasoning for difficult problems. |
| gpt-5.1-medium | 272,000 | 128,000 | Balanced intelligence and reasoning for complex tasks. |
| gpt-5.1-low | 272,000 | 128,000 | Efficient reasoning for moderately complex problems. |
| gpt-5.1 | 272,000 | 128,000 | Fastest and most capable model for all tasks, is not a reasoning model. |
| gpt-5-mini-high | 272,000 | 128,000 | Strong reasoning for complex tasks at a low cost. |
| gpt-5-mini-medium | 272,000 | 128,000 | Balanced reasoning for everyday complex problems. |
| gpt-5-mini-low | 272,000 | 128,000 | Light reasoning for simple to moderate tasks. |
| gpt-5-mini-minimal | 272,000 | 128,000 | Fast, cost-effective reasoning for simple agents. |
| gpt-realtime | 28,672 | 8,191 | Instant, short-context, voice-first realtime agent. Contains 10 different voice options to cover a range of use cases and tones. |
| gpt-realtime-1.5 | 32,000 | 4,096 | Enhanced voice model with improved reasoning, transcription accuracy, and tool calling. Contains 10 different voice options to cover a range of use cases and tones. |
Best Practices
- Use descriptive names so team members can quickly identify each agent’s role.
- Choose large-context models for complex reasoning and smaller, faster models for lightweight workflows.
- Test thoroughly after configuring each component to ensure accuracy and reliability.