> For the complete documentation index, see [llms.txt](https://docs.countercyclical.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.countercyclical.io/agents/providers-models-and-effort.md).

# Providers, Models, & Effort

Choose which AI provider, model, and reasoning effort Agents use for a task.

Select the model control beneath the Agents prompt to change its **Provider**, **Model**, or **Effort**.&#x20;

See also [Composer Preference](https://docs.countercyclical.io/agents/composer-preference) and [Governance](https://docs.countercyclical.io/agents/governance).

The current configuration is summarized directly in the control—for example, **OpenAI · 5.5 Sol · Medium**.

### Providers

The **Provider** setting determines which AI platform runs the agent. Available providers currently include:

* [**OpenAI**](https://openai.com/)
* [**Anthropic**](https://anthropic.com/)
* [**Gemini**](https://gemini.google.com/)
* [**Meta Muse**](https://ai.meta.com/muse)
* [**xAI**](https://x.ai/)

Changing providers also changes the models and effort levels available to that agent. Provider availability may evolve as additional models and integrations are supported.

### Models

Select **Model** to choose a model offered by the active provider.

For **OpenAI**, available models shown include:

* **GPT-6 Astra**
* **GPT-5.6 Sol**
* **GPT-5.6 Terra**
* **GPT-5.6 Luna**
* **GPT-5.5**
* **GPT-5.4**
* **GPT-5.4 Mini**, and&#x20;
* **GPT-5.4 Nano**

For **Anthropic**, available models shown include:&#x20;

* **Claude Fable 5.1**
* **Claude Opus 5**
* **Claude Sonnet 5**
* **Claude Fable 5**
* **Claude Opus 4.8**
* **Claude Sonnet 4.6**, and&#x20;
* **Claude Haiku 4.5**.

For **Gemini**, available models shown include:

* **Gemini 3.8 Flash**
* **Gemini 3.1 Pro Preview**
* **Gemini 3.5 Flash**
* **Gemini 2.5 Pro**
* **Gemini 2.5 Flash**, and&#x20;
* **Gemini 2.5 Flash-Lite**.

For **Meta Muse**, available models shown include:

* **Muse Spark 1.3**

For **xAI**, available models shown include:

* **Grok 4.6**
* **Grok 4.5**
* **Grok 4.3**

{% hint style="info" %}
Model availability is provider-specific and may change over time.
{% endhint %}

### Effort

**Effort** controls how much reasoning or computational effort the selected model uses for the agent's task. Higher settings can be useful for complex research, synthesis, analysis, or multi-step work, while lower settings are generally better suited to simpler tasks where speed is more important.

The effort levels available depend on the selected provider and model. The interface only presents supported settings for the current configuration.

For example, the configurations shown support ranges including:

**OpenAI GPT-5.5:** Low, Medium, High, Extra High, and Max.

**Anthropic Claude Fable 5:** Low, Medium, High, Extra High, and Max.

**Gemini 3.1 Pro Preview:** Low, Medium, and High.

**Meta Muse Muse Spark 1.3:** Low, Medium, High, and Extra High.

**xAI Grok 4.6:** Low, Medium, High, and Extra High.

{% hint style="info" %}
Changing effort does not change the selected provider or model.
{% endhint %}

### Choosing a Configuration

There is no single configuration that is optimal for every agent. Match the model and effort level to the work being performed.

Use lower effort for straightforward extraction, classification, formatting, or other predictable operations. Medium effort is a practical default for general research and analysis. Higher effort is more appropriate when an agent needs to reason across conflicting information, perform deeper analysis, synthesize substantial context, or make more difficult judgments.

For workflows containing multiple Agents, each Agent can use a different provider, model, and effort level. This allows simpler stages to use faster configurations while reserving more capable or higher-effort configurations for the parts of the workflow that require them.

#### Related Pages

{% content-ref url="/pages/k0lQRGr9ax4sWpRtvFpN" %}
[Composer Preference](https://docs.countercyclical.io/agents/composer-preference.md)
{% endcontent-ref %}

{% content-ref url="/pages/Rl2WZFJmGl0gjAjkDEyA" %}
[Governance](https://docs.countercyclical.io/agents/governance.md)
{% endcontent-ref %}

{% content-ref url="/pages/cF8IpbCXsAxGxbWhfba4" %}
[What is a Hierarchical Multi-Agentic System (HMAS)?](https://docs.countercyclical.io/agents/orchestrations/what-is-a-hierarchical-multi-agentic-system-hmas.md)
{% endcontent-ref %}
