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

# Models

VIVI supports a range of large language models, each suited to specific use cases. When selecting a model for your agent, consider the complexity of the tasks it needs to handle, the expected response speed, and cost.

Models are selected per agent under the **Model** section of the agent configuration screen.

***

## Reasoning Tiers

Many models are available in reasoning variants — **High**, **Medium**, **Low**, and in some cases **Minimal**. These tiers control how much thinking the model does before responding.

| Tier     | Behavior                                                                            |
| -------- | ----------------------------------------------------------------------------------- |
| High     | Deepest reasoning; slower but most accurate. Best for complex, multi-step problems. |
| Medium   | Balanced reasoning and speed. Good for most complex tasks.                          |
| Low      | Lightweight reasoning. Suitable for everyday problems where speed matters.          |
| Minimal  | Fastest and most cost-effective. Best for simple, high-volume agents.               |
| *(none)* | No reasoning overhead. Fastest response time for straightforward tasks.             |

***

## Available Models

| Model                  | Input (tokens) | Output (tokens) | Description                                                                                                         |
| ---------------------- | -------------- | --------------- | ------------------------------------------------------------------------------------------------------------------- |
| gpt-5.1 (High)         | 272k           | 128k            | Thorough reasoning for hard problems; slower but more accurate                                                      |
| gpt-5.1 (Medium)       | 272k           | 128k            | Balanced speed and reasoning for complex tasks                                                                      |
| gpt-5.1 (Low)          | 272k           | 128k            | Lightweight reasoning for everyday problems                                                                         |
| gpt-5.1                | 272k           | 128k            | Fast model for common tasks; no reasoning overhead                                                                  |
| gpt-5-mini (High)      | 136k           | 64k             | Strong reasoning for complex tasks at lower cost                                                                    |
| gpt-5-mini (Medium)    | 136k           | 64k             | Balanced reasoning for everyday complex problems                                                                    |
| gpt-5-mini (Low)       | 136k           | 64k             | Light reasoning for simple to moderate tasks                                                                        |
| gpt-5-mini (Minimal)   | 136k           | 64k             | Fast, cost-effective reasoning for simple agents                                                                    |
| gpt-5.2 (High)         | 272k           | 128k            | Thorough reasoning with higher precision for demanding problems                                                     |
| gpt-5.2 (Medium)       | 272k           | 128k            | Balanced speed and reasoning with improved accuracy                                                                 |
| gpt-5.2 (Low)          | 272k           | 128k            | Lightweight reasoning with better results for everyday problems                                                     |
| gpt-5.2                | 272k           | 128k            | Smarter and more accurate for common tasks; no reasoning overhead                                                   |
| gpt-5.3-codex (High)   | 272k           | 128k            | Maximum code reasoning for the most complex agentic coding workflows                                                |
| gpt-5.3-codex (Medium) | 272k           | 128k            | Balanced code reasoning for complex development tasks                                                               |
| gpt-5.3-codex (Low)    | 272k           | 128k            | Light code reasoning for routine development and automation                                                         |
| gpt-5.3-codex          | 272k           | 128k            | Code-optimized model for development and automation tasks; SWE-bench SOTA                                           |
| gpt-5.4 (High)         | 872k           | 128k            | Deepest reasoning available for the most challenging problems                                                       |
| gpt-5.4 (Medium)       | 872k           | 128k            | Balanced speed and top-tier reasoning for complex tasks                                                             |
| gpt-5.4 (Low)          | 872k           | 128k            | Lightweight reasoning with best-in-class results for everyday problems                                              |
| gpt-5.4                | 872k           | 128k            | Most intelligent model for common tasks; no reasoning overhead                                                      |
| gpt-5.4-mini (High)    | 272k           | 128k            | Strong reasoning at mini pricing for demanding tasks                                                                |
| gpt-5.4-mini (Medium)  | 272k           | 128k            | Balanced reasoning at mini pricing for complex everyday work                                                        |
| gpt-5.4-mini (Low)     | 272k           | 128k            | Lightweight reasoning at mini pricing for routine problems                                                          |
| gpt-5.4-mini           | 272k           | 128k            | Cost-efficient model balancing intelligence and speed; no reasoning overhead                                        |
| gpt-5.4-nano (High)    | 272k           | 128k            | Strong reasoning at nano pricing for latency-sensitive tasks                                                        |
| gpt-5.4-nano (Medium)  | 272k           | 128k            | Balanced reasoning at nano pricing for high-volume workloads                                                        |
| gpt-5.4-nano (Low)     | 272k           | 128k            | Lightweight reasoning at nano pricing for simple, high-throughput tasks                                             |
| gpt-5.4-nano           | 272k           | 128k            | Smallest and fastest model in the 5.4 family; no reasoning overhead                                                 |
| gpt-realtime           | 28,672         | 8,191           | Instant, short-context, voice-first realtime agent. 10 voice options available.                                     |
| gpt-realtime-1.5       | 32,000         | 4,096           | Enhanced voice model with improved reasoning, transcription accuracy, and tool calling. 10 voice options available. |

***

## Best Practices

* Use **gpt-5.4 (High)** or **gpt-5.1 (High)** for agents handling complex reasoning, legal, or technical content where accuracy is critical.
* Use **gpt-5-mini** or **gpt-5.4-nano** variants for high-volume, straightforward workflows where speed and cost matter more than depth.
* Use **gpt-5.3-codex** variants for agents that involve code generation, automation, or developer-facing workflows.
* Use **gpt-realtime** models only for voice-enabled agents — they are optimized for low-latency audio and are not suited for text-heavy or long-context tasks.
* When in doubt, start with a **Medium** reasoning tier and adjust based on response quality and latency in testing.