# Strategies

Strategies are evaluated by AI, produce [events](/ai/events.md), and trade on your behalf.

A strategy has the following properties:

<table><thead><tr><th width="200.9453125"></th><th></th></tr></thead><tbody><tr><td>Nickname</td><td>A descriptive name for the strategy, chosen by the user at strategy creation time - only used for display purposes</td></tr><tr><td>Markets</td><td>Markets that the strategy covers - any market not in this list will not be considered by the strategy - the more markets selected, the more AI credits the strategy consumes</td></tr><tr><td>Max Trade Quantity</td><td>Maximum USD quantity of orders submitted by the strategy - selected by the user at strategy creation time - users are recommended to start out with a low Max Trade Quantity and scale up as they refine their prompts and become more confident in their AI</td></tr><tr><td>Timeframe</td><td>The timeframe which the strategy operates on - can be anywhere from 1 minute to 1 week</td></tr><tr><td>Evaluation Frequency</td><td>The frequency at which the strategy is evaluated - can be anywhere from 1 second to 1 hour</td></tr><tr><td>Min. Confidence </td><td>Minimum confidence threshold required by the strategy in order to submit orders - traders are recommend to start out with a minimum confidence threshold of 90% and fine-tune as needed</td></tr><tr><td>Prompt</td><td>User-written text prompt which defines the strategy and tells the AI what to do - can be any in any natural language although English tends to yield the best results.</td></tr><tr><td>Status</td><td>Can be either "ACTIVE" or "PAUSED"  - "PAUSED" strategies do not trade and do not consume AI credits</td></tr><tr><td>Creation Time</td><td>Strategy creation time - time at which the user created the strategy</td></tr><tr><td>Model</td><td>The AI model employed by the strategy</td></tr><tr><td>Temperature</td><td>The temperature setting of the AI model employed by the strategy</td></tr><tr><td>Discretion</td><td>Whether the strategy employs discretion</td></tr><tr><td>Cost Savings Mode</td><td>Running the strategy in Cost Savings Mode can reduce token consumption by up to 30% - disabled by default</td></tr><tr><td>Lookback Period</td><td>Number of historical bars considered by the strategy - default is 5 - higher numbers result in increased token consumption</td></tr><tr><td>Trigger Strategy</td><td>When enabled, the strategy triggers a separate, unrelated strategy, instead of trading on its own - can be used to chain strategies together and to create screeners - disabled by default</td></tr><tr><td>Max Slippage</td><td>Maximum slippage tolerated by the strategy</td></tr></tbody></table>

The most important properties to understand are **Prompt**, **Timeframe** and **Min. Confidence**.&#x20;

**Prompt** is a user-written text in natural language (our AI models can handle any language - however, English tends to yield the best results). It defines the strategy and tells the AI what to do. It can include references to the data listed [here](/ai/supported-data.md). It has a maximum length of 5000 characters.

**Timeframe** determines the timeframe that the AI considers in its decision process, and the timeframe/horizon of the data that is sent to the AI as part of a query.

**Min. Confidence** is the minimum confidence level required by the AI in order to commit to a trading decision ("BUY" , "SELL" or "CLOSE"). The default minimum confidence level is 90%, requiring the AI to be reasonably certain in its decision prior to placing a trade. Traders can optionally select a lower minimum confidence level, resulting in more frequent trades and a potentially higher error/hallucination rate.

### Timeframes

Strategies can utilize the following timeframes:

| Timeframe | Description |
| --------- | ----------- |
| 1m        | 1 minute    |
| 3m        | 3 minutes   |
| 5m        | 5 minutes   |
| 15m       | 15 minutes  |
| 30m       | 30 minutes  |
| 1h        | 1 hour      |
| 2h        | 2 hours     |
| 4h        | 4 hours     |
| 6h        | 6 hours     |
| 24h       | 1 day       |

### Min. Confidence

Commonly selected min. confidence levels:

| Min. Confidence | Description                                                                                                                                            |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
| 95%             | Very conservative min. confidence level. Use this when you want the AI to be extremely sure about its decision prior to making a trade                 |
| 90%             | Default min. confidence level. Best for most strategies                                                                                                |
| 85%             | Aggressive min. confidence level. Use when you want the AI to trade more frequently and don't mind a higher "hallucination rate"                       |
| 80%             | Very aggressive min. confidence level. Use only when you want the AI to trade very frequently and are fine with occasional errors and "hallucinations" |

### Models

Strategies can utilize the following models:

<table><thead><tr><th width="235.16015625">Model</th><th width="136.51171875">Speed</th><th width="151.5703125">Cost Per Event</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>

### Strategy Costs

Strategies consume credits for each [event](/ai/events.md) that they generate. Below is a cost breakdown for a strategy that uses the GPT-4.1-Mini model:

<table><thead><tr><th width="191.7734375">Evaluation Frequency</th><th width="287.734375">Events Produced Per Market Per Day</th><th>Hourly Credit Usage Per Market</th></tr></thead><tbody><tr><td>1s</td><td>86400</td><td>$0.54</td></tr><tr><td>5s</td><td>17280</td><td>$0.108</td></tr><tr><td>15s</td><td>5760</td><td>$0.036</td></tr><tr><td>30s</td><td>2880</td><td>$0.018</td></tr><tr><td>1m</td><td>1440</td><td>$0.009</td></tr><tr><td>3m</td><td>480</td><td>$0.003</td></tr><tr><td>5m</td><td>288</td><td>$0.0018</td></tr><tr><td>15m</td><td>96</td><td>$0.0006</td></tr><tr><td>30m</td><td>48</td><td>$0.0003</td></tr><tr><td>1h</td><td>24</td><td>$0.00015</td></tr></tbody></table>


---

# Agent Instructions: 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:

```
GET https://references.everstrike.io/ai/strategies.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.