> For the complete documentation index, see [llms.txt](https://docs.convai.com/api-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.convai.com/api-docs/convai-playground/character-customization/core-ai-settings.md).

# Core AI Settings

## Introduction

The **Core AI Settings** section defines the foundational behavior of your AI character by controlling safety filters, the underlying language model, and the creativity level of its responses. These settings have a significant impact on how your character interacts with users, balancing safety, accuracy, and creativity.

<figure><img src="/files/HNjQijfPffnCnjW0NQfJ" alt=""><figcaption></figcaption></figure>

***

## Main Features

### 1. Enable Moderation Filter

* This setting allows you to filter out potentially harmful content, including hate speech, profanity, or inappropriate language. You can turn the moderation filter on or off using the toggle located at the top of the page. By default, this setting is enabled.

<figure><img src="/files/0wwKpI7mHzrBkXVhM5KW" alt=""><figcaption></figcaption></figure>

{% hint style="warning" %}
Disabling the Moderation Filter makes some foundation models unavailable.
{% endhint %}

{% hint style="warning" %}
Features like **Narrative Design** and **Multilingual support** will not work when moderation is disabled.
{% endhint %}

***

### 2. Select Foundation Model

Choose from a variety of **Large Language Models (LLMs)** from leading providers:

* OpenAI
* Anthropic
* Google
* Llama

<figure><img src="/files/hkeeW7MtoY1zElevbVmM" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
Model availability depends on whether the Moderation Filter is enabled.
{% endhint %}

***

### Supported LLMs

Below is a list of Large Language Models (LLMs) available in the Convai Playground under **Core AI Settings**.\
Models marked as ✅ *Flagship* are the providers’ top-tier, most capable models — but usage of these is subject to the **Flagship Interaction Cap** based on your plan.

> **Flagship LLMs**\
> This is the limit on the number of interactions you can perform using Flagship LLMs.
>
> **Example:**\
> In the *Indie Dev* plan, you have a total monthly quota of **3000 Interactions**. However, the **Flagship LLM Interaction Cap** is **1500**.\
> If you use GPT-4.1 after 1500 interactions, your Flagship LLM quota will be exhausted.\
> You will then need to switch to a non-Flagship LLM for the remaining 1500 interactions.

***

### Realtime / Live Models

#### OpenAI

<table><thead><tr><th>Model</th><th>Model Code</th><th data-type="checkbox">Flagship</th></tr></thead><tbody><tr><td>GPT Realtime 1.5 (beta)</td><td>gpt-realtime-1.5</td><td>false</td></tr><tr><td>GPT Realtime Mini (beta)</td><td>gpt-realtime-mini</td><td>false</td></tr></tbody></table>

#### Google

<table><thead><tr><th>Model</th><th>Model Code</th><th data-type="checkbox">Flagship</th></tr></thead><tbody><tr><td>Gemini 2.5 Flash Live (beta)</td><td>gemini-2.5-flash-live</td><td>false</td></tr><tr><td>Gemma 4 31B Fast (beta)</td><td>realtime-gemma-4-31b-it</td><td>false</td></tr><tr><td>Gemma 4 26B A4B Fast (beta)</td><td>realtime-gemma-4-26b-a4b-it</td><td>false</td></tr></tbody></table>

### Standard Models

#### OpenAI

<table><thead><tr><th>Model</th><th>Model Code</th><th data-type="checkbox">Flagship</th></tr></thead><tbody><tr><td>GPT-5.4</td><td>gpt-5.4</td><td>false</td></tr><tr><td>GPT-5.x (latest)</td><td>gpt-5.x</td><td>true</td></tr><tr><td>GPT-OSS-120B (beta)</td><td>gpt-oss-120b</td><td>false</td></tr><tr><td>GPT-5.1 (beta)</td><td>gpt-5.1</td><td>false</td></tr><tr><td>GPT-4.1</td><td>gpt-4.1</td><td>false</td></tr><tr><td>GPT-5.4-nano</td><td>gpt-5.4-nano</td><td>false</td></tr><tr><td>GPT-5.x-nano (latest)</td><td>gpt-5.x-nano</td><td>true</td></tr><tr><td>GPT-5.4-mini</td><td>gpt-5.4-mini</td><td>false</td></tr><tr><td>GPT-5.x-mini (latest)</td><td>gpt-5.x-mini</td><td>true</td></tr><tr><td>GPT-4.1-mini</td><td>gpt-4.1-mini</td><td>false</td></tr><tr><td>GPT-5.3 Instant</td><td>gpt-5.3-instant</td><td>false</td></tr><tr><td>GPT-4o</td><td>gpt-4o</td><td>false</td></tr><tr><td>GPT-4.1-nano</td><td>gpt-4.1-nano</td><td>false</td></tr><tr><td>GPT-4o-mini</td><td>gpt-4o-mini</td><td>false</td></tr></tbody></table>

#### Anthropic

<table><thead><tr><th>Model</th><th>Model Code</th><th data-type="checkbox">Flagship</th></tr></thead><tbody><tr><td>Claude 4.5 Sonnet (beta)</td><td>claude-4-5-sonnet</td><td>false</td></tr><tr><td>Claude 4.5 Haiku (beta)</td><td>claude-4-5-haiku</td><td>false</td></tr><tr><td>Claude Sonnet (latest)</td><td>claude-sonnet</td><td>true</td></tr><tr><td>Claude Haiku (latest)</td><td>claude-haiku</td><td>true</td></tr></tbody></table>

#### Google

<table><thead><tr><th>Model</th><th>Model Code</th><th data-type="checkbox">Flagship</th></tr></thead><tbody><tr><td>Gemini 3.5 Flash</td><td>gemini-3.5-flash</td><td>false</td></tr><tr><td>Gemini Flash (latest)</td><td>gemini-flash</td><td>true</td></tr><tr><td>Gemini 3.1 Flash Lite</td><td>gemini-3.1-flash-lite</td><td>false</td></tr><tr><td>Gemini Flash Lite (latest)</td><td>gemini-flash-lite</td><td>true</td></tr><tr><td>Gemini 2.5 Flash</td><td>gemini-2.5-flash</td><td>false</td></tr><tr><td>Gemini 2.5 Flash Lite</td><td>gemini-2.5-flash-lite</td><td>false</td></tr></tbody></table>

#### Qwen

<table><thead><tr><th>Model</th><th>Model Code</th><th data-type="checkbox">Flagship</th></tr></thead><tbody><tr><td>Qwen3.6 27B (beta)</td><td>qwen3.6-27b</td><td>false</td></tr><tr><td>Qwen3.6 35B A3B (beta)</td><td>qwen3.6-35b-a3b</td><td>false</td></tr></tbody></table>

#### Llama

<table><thead><tr><th>Model</th><th>Model Code</th><th data-type="checkbox">Flagship</th></tr></thead><tbody><tr><td>Llama 4 Maverick (beta)</td><td>llama-4-maverick</td><td>false</td></tr><tr><td>Llama 4 Scout (beta)</td><td>llama-4-scout</td><td>false</td></tr><tr><td>Llama3 70B</td><td>llama3-70b</td><td>false</td></tr></tbody></table>

#### xAI

<table><thead><tr><th>Model</th><th>Model Code</th><th data-type="checkbox">Flagship</th></tr></thead><tbody><tr><td>Grok 4.3</td><td>grok-4.3</td><td>false</td></tr></tbody></table>

***

### 3. Temperature Control

<figure><img src="/files/JP4b5xWRmNClhbczheM4" alt=""><figcaption></figcaption></figure>

* **Function:** Adjusts the randomness and creativity in the AI’s responses.
* **Slider Range:** `0.0` (most deterministic) to `1.0` (most creative).

| Temperature Range    | Behavior                                   | Use Case                                       |
| -------------------- | ------------------------------------------ | ---------------------------------------------- |
| **Low (0.0–0.3)**    | Deterministic, consistent                  | Factual Q\&A, compliance-critical interactions |
| **Medium (0.4–0.7)** | Balanced accuracy and creativity           | Conversational agents, customer support        |
| **High (0.8–1.0)**   | Diverse, creative, sometimes unpredictable | Storytelling, brainstorming, roleplay          |

{% hint style="info" %}
Lower temperature sharpens the probability distribution for more predictable word choices.

Higher temperature flattens the distribution, allowing less likely words to appear more frequently.
{% endhint %}

***

### 4. Reasoning Level

Found under **Advanced Settings**, next to Temperature.

* **Function:** Controls how much internal reasoning the model does before answering.
* **Availability:** Only shown for models that support it. Models without reasoning control — such as the Gemma, Llama, Qwen and GLM families — do not display this setting.

Reasoning trades latency for answer quality. More reasoning generally produces better handling of multi-step questions and instructions, at the cost of a slower first response.

#### Available options

The exact list depends on the selected model, because each provider exposes a different scale.

| Option                | Behavior                                                                                                             |
| --------------------- | -------------------------------------------------------------------------------------------------------------------- |
| **Auto**              | No level is sent. The model applies its own adaptive default, reasoning more on hard requests and less on easy ones. |
| **Off** / **Minimal** | The lowest setting the model offers. Fastest first response.                                                         |
| **Low**               | A small amount of reasoning.                                                                                         |
| **Medium**            | Balanced. Most providers' own default.                                                                               |
| **High** and above    | Maximum reasoning. Slowest, best on complex multi-step requests.                                                     |

{% hint style="info" %}
**Auto is usually the right starting point.** Current models already adapt their own reasoning to the difficulty of each request, so Auto typically keeps easy turns fast while still allowing the model to think when a request genuinely needs it. Pin an explicit level when you need predictable latency, or when you have measured that a specific level performs better for your use case.
{% endhint %}

{% hint style="warning" %}
Higher reasoning levels increase both response latency and token consumption. If your experience is latency-sensitive — a live voice agent, for example — measure the effect before raising the level.
{% endhint %}

#### Switching models

If you change the foundation model, your reasoning level is kept when the new model also supports it. When it does not, the setting falls back to **Auto**, so the character never sends a value its model would reject.

#### Characters created before this setting existed

Characters that have never had a reasoning level set show **Model default** and keep the behavior they have always had. Editing and saving other settings will not change this. Selecting any other option opts the character in, and there is no way back to **Model default** afterwards — choose **Auto** if you want the model to decide.

***

## Conclusion

The Core AI Settings give you precise control over your character’s foundation model, safety filters, and response style. By adjusting these parameters, you can create an AI that balances safety, reliability, and creativity to suit your specific application.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.convai.com/api-docs/convai-playground/character-customization/core-ai-settings.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.