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

# Text models (LLMs)

Text models enhance prompts and process context throughout your flows' work.

In Pletor, text models' primary role is often behind-the-scenes: refining user inputs, processing brand guidelines, and creating optimized prompts for image and video generation models. They act as intelligent intermediaries that transform raw context into polished instructions for other AI nodes.

## What text model should I pick?

The right model depends on your specific workflow requirements. When in doubt, start with a balanced model you already know, and adjust based on your use case and results:

| Use case                                    | Recommended models                                        |
| ------------------------------------------- | --------------------------------------------------------- |
| Prompt enhancement                          | Gemini 3.5 Flash, Claude Sonnet 5.5                       |
| Large context or brand guideline processing | Gemini 3.1 Pro, Claude Opus 5.5, GPT-6.1 Sol, Muse Wonder |
| Hardest briefs and deep reasoning           | Claude Fable 5.2, GPT-6 Astra                             |
| Video or audio inputs                       | Gemini 3.1 Pro, Gemini 3.8 Flash                          |
| Fast, real-time workflows                   | Gemini 3.8 Flash, Claude Haiku 5.5                        |
| Resource-conscious workflows                | Claude Haiku 5.5                                          |

Gemini Flash models and Claude Haiku 4.5 cost no credits per run. Turning on web search or high reasoning effort adds half a credit to any model.

## Choosing the right model

### Best practices

* **Match model to task**: Use faster models for simple prompt crafting, balanced models when you need more creativity.
* **Consider context needs**: If your workflow involves extensive brand guidelines or reference materials, choose models with larger context windows.
* **Test different models**: The same prompt can yield different styles, experiment to find what works best for your use case.

### Go-to models (for most workflows)

Start with these reliable, balanced models that handle the majority of prompt enhancement and context processing tasks:

* **Gemini 3.5 Flash** - Google's fast multimodal model. Free to run, with strong reasoning and large-context handling. Ideal for quick prompt generation and real-time workflows.
* **Claude Sonnet 5.5** - Anthropic's best combination of speed and intelligence. Our pick for routine prompt enhancement, brand guideline processing and context work.

### When working with extensive or multimodal context

Select these models for complex briefs and large amounts of context:

* **Gemini 3.1 Pro** - Handles complex briefs with extensive brand guidelines material or media creative analysis, including video and audio. Can process and reference large amounts of context simultaneously.
* **Claude Opus 5.5** - Strong reasoning for long, multi-step briefs, document creation and context analysis. Costs twice the credits of Sonnet 5.5 and does not read video or audio.
* **GPT-6.1 Sol** - OpenAI's model for complex professional work. Similar to Claude Opus.
* **Muse Wonder** - Meta's most capable model, built for long, multi-step work that follows detailed instructions closely. 1M-token context, reads images. In preview at Meta.

### When you need the most capable model

Keep these for the briefs that truly need them: they cost 8 credits per run, four times Opus.

* **Claude Fable 5.2** - Anthropic's most capable widely available model, for demanding reasoning, long-horizon work and multi-step research.
* **GPT-6 Astra** - OpenAI's most capable model, for complex reasoning, research and document creation.

### When speed is your priority

Choose these models when you need fast generation and real-time performance:

* **Gemini 3.8 Flash** - Google's latest fast multimodal model, reading text, images, audio and video. Free to run, and built for long, multi-step work.
* **Claude Haiku 5.5** - Anthropic's fastest model, for prompt enhancement, summarization and quick context processing. Reads images; supports web search, structured output and adaptive reasoning.

### Video and audio inputs

Gemini models and Muse Wonder read video and audio; in Pletor, those inputs go to Gemini models only. When you connect a video or audio input to a text node, the model list narrows to Gemini models, and a node set to another model switches to Gemini 3 Flash.

### Older models

Earlier versions (Claude Fable 5.1, Opus 5, Sonnet 5, Sonnet 4.6, Opus 4.5 to 4.7, Haiku 4.5, GPT-5.x and GPT-4.1, Gemini 3 and 2.5, o3) stay available in the model picker. Claude Sonnet 4.5 (retired Nov 3, flows moved to Sonnet 5.5) and GPT-5.3 are no longer available. For new flows, start with the models above.
