> 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/api-reference/core-api-reference/character-crafting-apis/core-ai-settings-api.md).

# Core AI Settings API

{% hint style="danger" %}
This API is available only on the Professional Plan and above.
{% endhint %}

## Character Model Selection

<mark style="color:green;">`POST`</mark> `https://api.convai.com/character/update`

Update API can be used to change the LLM to be used for Character. Currently following models are supported.

### 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>

When calling update API to update Model for your Character, please ensure to pass the `Model Code` corresponding to the `Model` from the table above.

#### Headers

| Name                                             | Type   | Description                                                                                                |
| ------------------------------------------------ | ------ | ---------------------------------------------------------------------------------------------------------- |
| CONVAI-API-KEY<mark style="color:red;">\*</mark> | String | The unique api-key provided for every user. Found under the Key icon when logged into your Convai account. |

#### Request Body

| Name               | Type   | Description                                                               |
| ------------------ | ------ | ------------------------------------------------------------------------- |
| charID             | String | Id of your character.                                                     |
| model\_group\_name | String | Model Code of the Model to which you want to update. See the table above. |

{% tabs %}
{% tab title="200: OK The model has been sucessfuly updated." %}

```json
{"STATUS": "SUCCESS"}
```

{% endtab %}

{% tab title="401 API Key validation has failed" %}

```json
{
    "API_ERROR": "Invalid API key provided.
}
```

{% endtab %}
{% endtabs %}

Here are some sample codes to demonstrate the request format for the endpoint -->

{% tabs %}
{% tab title="Python" %}
{% code overflow="wrap" %}

```python
import requests
import json

url = "https://api.convai.com/character/update"

headers = { 
    'CONVAI-API-KEY': '<Your-API-Key>',
    'Content-Type': 'application/json'
}

# Create a dictionary for the JSON payload
payload = { 
    "charID": "<Your-Character-Id>",
    "model_group_name": "claude-3-5-sonnet"
}

# Convert the payload to JSON
json_payload = json.dumps(payload)

response = requests.post(url, headers=headers, data=json_payload)

print(response.text)

```

{% endcode %}
{% endtab %}

{% tab title="cURL" %}
{% code overflow="wrap" %}

```shell
curl -X POST "https://api.convai.com/character/update" \
     -H "CONVAI-API-KEY: <Your-API-Key>" \
     -H "Content-Type: application/json" \
     -d '{
           "charID": "<Your-Character-Id>",
           "model_group_name": "claude-3-5-sonnet"
         }'
```

{% endcode %}
{% endtab %}
{% endtabs %}

## Temperature Setting

<mark style="color:green;">`POST`</mark> `https://api.convai.com/character/update`

When chatting with AI, the temperature setting is like adjusting how creative or predictable the responses will be. A lower temperature makes the AI stick closer to what it knows for sure (Less Hallucinations), while a higher temperature lets it get more imaginative and potentially surprising (better Role Play).

#### Headers

| Name                                             | Type   | Description                                                                                                |
| ------------------------------------------------ | ------ | ---------------------------------------------------------------------------------------------------------- |
| CONVAI-API-KEY<mark style="color:red;">\*</mark> | String | The unique api-key provided for every user. Found under the Key icon when logged into your Convai account. |

#### Request Body

| Name        | Type   | Description                                 |
| ----------- | ------ | ------------------------------------------- |
| charID      | String | Id of your character.                       |
| temperature | Float  | Temperature value. Must be between 0 and 1. |

{% tabs %}
{% tab title="200: OK Temperature Successfully Updated" %}

```json
{"STATUS": "SUCCESS"}
```

{% endtab %}

{% tab title="401 API Key validation has failed" %}

```json
{
    "API_ERROR": "Invalid API key provided.
}
```

{% endtab %}
{% endtabs %}

Here are some sample codes to demonstrate the request format for the endpoint -->

{% tabs %}
{% tab title="Python" %}
{% code overflow="wrap" %}

```python
import requests
import json

url = "https://api.convai.com/character/update"

headers = { 
    'CONVAI-API-KEY': '<Your-API-Key>',
    'Content-Type': 'application/json'
}

# Create a dictionary for the JSON payload
payload = { 
    "charID": "<Your-Character-Id>",
    "temperature": 0.42
}

# Convert the payload to JSON
json_payload = json.dumps(payload)

response = requests.post(url, headers=headers, data=json_payload)

print(response.text)

```

{% endcode %}
{% endtab %}

{% tab title="cURL" %}
{% code overflow="wrap" %}

```shell
curl -X POST "https://api.convai.com/character/update" \
     -H "CONVAI-API-KEY: <Your-API-Key>" \
     -H "Content-Type: application/json" \
     -d '{
           "charID": "<Your-Character-Id>",
           "temperature": 0.42
         }'
```

{% endcode %}
{% endtab %}
{% endtabs %}

***

## Reasoning Level Setting

<mark style="color:green;">`POST`</mark> `https://api.convai.com/character/update`

Controls how much internal reasoning the model performs before answering. More reasoning generally improves multi-step questions and instruction following, at the cost of higher latency and token usage.

Support is per model. Query [`/character/getSupportedModel`](#discovering-supported-reasoning-levels) to find out which levels a model accepts before setting one — a value the model does not support is rejected.

#### Headers

| Name                                             | Type   | Description                                                                                                |
| ------------------------------------------------ | ------ | ---------------------------------------------------------------------------------------------------------- |
| CONVAI-API-KEY<mark style="color:red;">\*</mark> | String | The unique api-key provided for every user. Found under the Key icon when logged into your Convai account. |

#### Request Body

| Name              | Type   | Description                                                                                  |
| ----------------- | ------ | -------------------------------------------------------------------------------------------- |
| charID            | String | Id of your character.                                                                        |
| reasoning\_effort | String | A level the selected model supports, or `"auto"`. Send an empty string to clear the setting. |

#### Values

| Value             | Behavior                                                                                                                                                  |
| ----------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
| *(not set)*       | The character inherits whatever the model is configured with. This is the state of every character that has never had a level set.                        |
| `"auto"`          | No reasoning parameter is sent to the provider, so the model applies its own adaptive default — reasoning more on hard requests and less on easy ones.    |
| A supported level | Sent to the provider explicitly. Common values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh` and `max`, but the accepted set is model-specific. |

{% hint style="warning" %}
**Not set and `"auto"` are different.** Not set preserves the model's configured behavior. `"auto"` actively suppresses it so the provider's own adaptive default applies. Sending an empty string clears the setting and returns the character to the not-set state.
{% endhint %}

{% tabs %}
{% tab title="200: OK Reasoning level successfully updated" %}

```json
{"STATUS": "SUCCESS"}
```

{% endtab %}

{% tab title="400 Unsupported level for this model" %}

```json
{
    "ERROR": "Invalid reasoning_effort 'xhigh' for model 'gemini-3.6-flash'. Supported values: minimal, low, medium, high, auto."
}
```

{% endtab %}

{% tab title="401 API Key validation has failed" %}

```json
{
    "API_ERROR": "Invalid API key provided."
}
```

{% endtab %}
{% endtabs %}

{% tabs %}
{% tab title="Python" %}
{% code overflow="wrap" %}

```python
import requests
import json

url = "https://api.convai.com/character/update"

headers = {
    'CONVAI-API-KEY': '<Your-API-Key>',
    'Content-Type': 'application/json'
}

payload = {
    "charID": "<Your-Character-Id>",
    "reasoning_effort": "auto"
}

response = requests.post(url, headers=headers, data=json.dumps(payload))

print(response.text)
```

{% endcode %}
{% endtab %}

{% tab title="cURL" %}
{% code overflow="wrap" %}

```shell
curl -X POST "https://api.convai.com/character/update" \
     -H "CONVAI-API-KEY: <Your-API-Key>" \
     -H "Content-Type: application/json" \
     -d '{
           "charID": "<Your-Character-Id>",
           "reasoning_effort": "auto"
         }'
```

{% endcode %}
{% endtab %}
{% endtabs %}

### Discovering supported reasoning levels

<mark style="color:green;">`POST`</mark> `https://api.convai.com/character/getSupportedModel`

Models that support reasoning control carry a `reasoning` block in their entry. Models without one do not support the setting.

```json
{
  "model_group_name": "gpt-5.6-luna-none",
  "display_name": "GPT-5.6 Luna",
  "reasoning": {
    "levels": ["none", "low", "medium", "high"],
    "supports_auto": true,
    "default": "medium"
  }
}
```

| Field          | Type      | Description                                                                      |
| -------------- | --------- | -------------------------------------------------------------------------------- |
| levels         | String\[] | The levels this model accepts, ordered from least to most reasoning.             |
| supports\_auto | Boolean   | Whether `"auto"` is a valid value for this model.                                |
| default        | String    | The provider's own default level, when known. Applies when `"auto"` is selected. |

{% hint style="info" %}
Build any level picker from this block rather than hardcoding a list. Providers add and rename levels over time, and the accepted set differs between model families — Gemini's lowest level is `minimal` while OpenAI's is `none`.
{% endhint %}


---

# 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/api-reference/core-api-reference/character-crafting-apis/core-ai-settings-api.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.