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

# Models

Strategies on Everstrike can utilize the following models:

<table><thead><tr><th width="235.16015625">Model</th><th width="136.51171875">Speed</th><th width="173.26171875">Cost Per Evaluation</th><th>Description</th></tr></thead><tbody><tr><td>GPT-4o-mini</td><td>1s</td><td>$0.000125</td><td>Oldest model.</td></tr><tr><td>GPT-4.1</td><td>1.5s</td><td>$0.0015</td><td>Fast, expensive and powerful model.</td></tr><tr><td>GPT-4.1-mini</td><td>1s</td><td>$0.00015</td><td>Default model. Best for most strategies.</td></tr><tr><td>GPT-4.1-nano</td><td>0.5s</td><td>$0.000075</td><td>Very fast and very cheap model.</td></tr><tr><td>GPT-5-mini-minimal-reasoning</td><td>3s</td><td>$0.0002</td><td>Balanced model.</td></tr><tr><td>GPT-5-nano-minimal-reasoning</td><td>3s</td><td>$0.00005</td><td>Cheap model.</td></tr><tr><td>GPT-5-mini-low-reasoning</td><td>5s</td><td>$0.0004</td><td>Slow and moderately powerful model.</td></tr><tr><td>GPT-5-nano-low-reasoning</td><td>5s</td><td>$0.0001</td><td>Slow, cheap and moderately powerful model.</td></tr><tr><td>GPT-5-mini-medium-reasoning</td><td>10s</td><td>$0.0008</td><td>Slow and powerful model.</td></tr><tr><td>GPT-5-nano-medium-reasoning</td><td>10s</td><td>$0.0002</td><td>Slow and moderately powerful model.</td></tr><tr><td>GPT-5-mini-high-reasoning</td><td>20s</td><td>$0.002</td><td>Slow, expensive and very powerful model.</td></tr><tr><td>GPT-5-nano-high-reasoning</td><td>20s</td><td>$0.0004</td><td>Slow and powerful model.</td></tr></tbody></table>

Notes:&#x20;

* Strategies with an evaluation frequency of 15 seconds or less are restricted to the GPT-4.1-nano model.
* The listed model speed is an average. In reality, the speed depends not only on the model, but also on the user prompt and the data that the model has to consider. There is no guarantee that a model will finish its evaluation within the specified time.
* The cost per evaluation can be reduced by restricting the amount of data that a strategy has access to. This can result in cost savings up to 50%. See [Supported Data](/ai/supported-data.md) for a list of data points that you may include or exclude.


---

# 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://references.everstrike.io/ai/models.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.