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

# AI Models for Strategy Evaluation: Speed and Cost Guide

> Compare AI models for strategy evaluation. Balance speed, cost per event, and reasoning depth to match the right model to your trading style.

Every AI strategy on Everstrike uses a specific model to evaluate markets and decide whether to trade. Your model choice has a direct impact on two things: how quickly each evaluation completes and how many credits each evaluation consumes. Models with deeper reasoning produce richer analysis but cost more and take longer. Faster models cost less and suit strategies that check often. Select the model that best fits your strategy's evaluation frequency, complexity, and cost budget.

## Available Models

| Model | Typical Speed | Cost per Evaluation | Description |
| - | - | - | - |
| **GPT-6 Luna** | 2–5s | \$0.0005 | **Default.** Tuned for trading decisions rather than conversation. Inexpensive. |
| GPT-5.6 Luna | — | \$0.0005 | The previous Luna model. |
| GPT-5.4-mini | — | \$0.0005 | Balanced speed and analysis. |
| GPT-5.4-nano | — | \$0.001 | A smaller model. |
| GPT-4.1 | 1.5s | \$0.004 | Powerful and expensive. |
| GPT-4.1-mini | 1s | \$0.0005 | A reliable all-rounder. |
| GPT-4.1-nano | 0.5s | \$0.0002 | **The fastest model.** The only one for strategies that check every 15 seconds or faster. |
| GPT-4o-mini | 1s | \$0.0002 | Oldest model. |
| GPT-5-mini-minimal-reasoning | 3s | \$0.0005 | Balanced. |
| GPT-5-nano-minimal-reasoning | 3s | \$0.0001 | The least expensive option. |
| GPT-5-mini-low-reasoning | 5s | \$0.001 | Moderately powerful. |
| GPT-5-nano-low-reasoning | 5s | \$0.0002 | Inexpensive and moderately powerful. |
| GPT-5-mini-medium-reasoning | 10s | \$0.0025 | Powerful. |
| GPT-5-nano-medium-reasoning | 10s | \$0.0005 | Inexpensive and powerful. |
| GPT-5-mini-high-reasoning | 20s | \$0.005 | Very powerful and expensive. |
| GPT-5-nano-high-reasoning | 20s | \$0.001 | Powerful and inexpensive. |

Speeds listed are averages, not guarantees; a dash means the model has not been benchmarked yet. Actual evaluation time also depends on prompt length and the amount of data available to the model during each run.

**What that costs in practice:** with GPT-6 Luna, a strategy that checks one market every hour costs about 2 cents a day, and one that checks every minute costs about \$0.06 an hour (each check costs the model's price once for the strategy plus once per market). The **Preview** tab shows the expected cost of any strategy before you submit it.

![Daily cost of a one-market GPT-6 Luna strategy by frequency](https://mintcdn.com/everstrike-50e7a7f9/2qtJozkzDkOYul4J/images/help/evaluation-cost.png?fit=max\&auto=format\&n=2qtJozkzDkOYul4J\&q=85\&s=bf2bec6102749411575a1533c1908c75)

What checking more often costs.

## Evaluation Frequency Limit

> [!NOTE]
>
> Strategies with an evaluation frequency of **15 seconds or less** can only use `GPT-4.1-nano`. This restriction ensures evaluations complete fast enough to keep up with the chosen frequency.

## Choosing the Right Model

Different strategies call for different models. Use the guidance below as a starting point:

> [card] Most Strategies
>
> **GPT-6 Luna** is the default: tuned for trading and inexpensive at \$0.0005 per evaluation, typically answering in 2–5 seconds. Start here unless you have a specific reason to switch.

> [card] Lowest Cost
>
> **GPT-5-nano with minimal reasoning** has the lowest cost per evaluation, at the price of a few seconds per check. It suits strategies that check infrequently.

> [card] More Analytical Power
>
> **GPT-5-mini with medium or high reasoning** provides deeper market analysis. Use it for complex prompts where reasoning quality matters more than speed or cost.

> [card] High-Frequency (15s or Less)
>
> **GPT-4.1-nano** is the only model available for strategies with an evaluation frequency of 15 seconds or less.

> [!TIP]
>
> Restricting the data available to your strategy can reduce the cost per evaluation by up to **50%** on most models (less on the reasoning models). Review the [Supported Data](https://docs.everstrike.io/ai/supported-data.md) page to remove data points your prompt doesn't need, and add [extra data sources](https://docs.everstrike.io/ai/supported-data.md#extra-data-sources) only when your rules use them.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.