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

# Text models

> The LLM families that power text generation, assistants, and LLM-based logic nodes.

Text models are large language models you can select on any text-generating node. They power [Generate Text](/nodes/ai-text/generate-text), and run under the hood in LLM-based logic nodes like [Switch](/nodes/logic/switch) and If / Else.

## Families

<Note>
  Model availability changes over time. The list below reflects the families currently supported. Pick a model from the node's model selector.
</Note>

| Family | Provider  | Notable models                                                                                                                                                   | Good for                                                            |
| ------ | --------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------- |
| Claude | Anthropic | Fable 5, Opus 4.8 (Standard / Fast), Sonnet 5, Opus 4.6, Opus 4.5, Opus 4.1, Opus 4, Sonnet 4.6, Sonnet 4.5, Sonnet 4, Haiku 4.5                                 | Long-form writing, reasoning, careful instruction-following         |
| Gemini | Google    | Gemini 3.5 Flash, Gemini 3.1 Pro, Gemini 3.1 Flash Lite, Gemini 3 Pro, Gemini 3 Flash, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash Lite, Gemini 2.0 Flash | Fast classification and routing, multimodal input, high-volume runs |
| OpenAI | OpenAI    | GPT-5.5 (Standard / Pro), GPT-5.4, GPT-5.4 Mini, GPT-5.2, GPT-5.1, GPT-5, GPT-4.1, GPT-4.1 Mini, o3                                                              | General-purpose generation, structured output, reasoning            |

Some models come in quality tiers you pick right on the node — for example Claude Opus 4.8's **Fast** tier runs the same model at higher output speed for a higher per-token price, and GPT-5.5's **Pro** tier trades cost for harder reasoning. The credit estimate updates as you switch tiers.

## Settings

Text models share a common set of options on the node. Availability depends on the model you pick.

| Setting                                    | What it does                                                                                                                 |
| ------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------- |
| `reasoning_effort`                         | How much the model thinks before answering. Higher effort improves quality on hard tasks at the cost of latency and credits. |
| `enable_web_search`                        | Lets the model look up current information on the web while generating.                                                      |
| Structured output (`output_schema_preset`) | Constrains the output to a defined shape so downstream nodes receive predictable fields.                                     |

See [Model settings](/models/settings) for the full reference.

## Related nodes

<Card title="Generate Text" href="/nodes/ai-text/generate-text">
  Generate text from a prompt, with optional media attachments and brand context. Pick a creative
  assistant to pre-fill an expert prompt for image prompting, ad copy, brand analysis, and more.
</Card>

LLM-based logic nodes such as [Switch](/nodes/logic/switch) and If / Else also run a text model to evaluate their conditions.