> 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/strategies.md). # Strategies Strategies are evaluated by AI, produce [events](/ai/events.md), and can trade on your behalf. Each active strategy produces one event per evaluation for each selected market. Paused strategies produce no events, place no trades, and consume no AI credits. {% hint style="warning" %} Start with one market and a low **Max Trade Quantity**. Review events before increasing exposure or evaluation frequency. {% endhint %} ### Configuration | Property | Description | | -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- | | Nickname | Display name chosen when you create the strategy. | | Markets | Markets the strategy evaluates. Unselected markets are ignored. Each selected market increases credit use. | | Max Trade Quantity | Maximum USD value for each order. Start low, then increase it as you validate the strategy. | | Timeframe | Data horizon used for the strategy's decisions. | | Evaluation Frequency | How often the strategy evaluates each selected market. More frequent evaluations create more events and cost more. | | Min. Confidence | Confidence required before the AI submits a `BUY`, `SELL`, or `CLOSE` order. | | Prompt | Instructions that define the strategy. Prompts support natural language and allow up to 5,000 characters. English usually produces the best results. | | Status | `ACTIVE` strategies evaluate and may trade. `PAUSED` strategies do neither. | | Creation Time | Time when you created the strategy. | | Model | AI model used for evaluations. | | Temperature | Temperature setting used by the model. | | Discretion | Whether the strategy uses discretion. | | Cost Savings Mode | Can reduce token consumption by up to 30%. Disabled by default. Reasoning output is minimal for events created in this mode. | | Lookback Period | Historical bars considered during evaluation. The default is 5. Higher values increase token consumption. | | Trigger Strategy | Triggers another strategy rather than trading directly. Use it to chain strategies or build screeners. Disabled by default. | | Max Slippage | Maximum slippage the strategy accepts. | ### Key controls #### Prompt The prompt tells the AI what to evaluate and how to act. It can reference the [supported data](/ai/supported-data.md). Make prompts specific about: * Markets or conditions to evaluate. * Entry, exit, and position-management rules. * When the strategy should hold instead of trading. #### Timeframe The timeframe sets the data horizon used during each decision. Choose a timeframe that matches your trading horizon. #### Min. Confidence The default is 90%. A lower threshold can create more trades, but may increase incorrect decisions. ### 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 Common confidence settings: | Min. Confidence | Description | | --------------- | --------------------------------------------------------------------------- | | 95% | Very conservative. Use when decisions need very high certainty. | | 90% | Default. Suitable for most strategies. | | 85% | Aggressive. May trade more often and make more incorrect decisions. | | 80% | Very aggressive. Use only when frequent trades justify a higher error rate. | ### Models Strategies can utilize the following models: | Model | Typical speed | Cost per event | Description | | ---------------------------- | ------------- | -------------- | ---------------------------------------- | | GPT-4o-mini | 1s | $0.000125 | Oldest model. | | GPT-4.1 | 1.5s | $0.0015 | Fast, expensive, and powerful. | | GPT-4.1-mini | 1s | $0.00015 | Default model. Best for most strategies. | | GPT-4.1-nano | 0.5s | $0.000075 | Very fast and inexpensive. | | GPT-5-mini-minimal-reasoning | 3s | $0.0002 | Balanced. | | GPT-5-nano-minimal-reasoning | 3s | $0.00005 | Inexpensive. | | GPT-5-mini-low-reasoning | 5s | $0.0004 | Moderately powerful. | | GPT-5-nano-low-reasoning | 5s | $0.0001 | Inexpensive and moderately powerful. | | GPT-5-mini-medium-reasoning | 10s | $0.0008 | Powerful. | | GPT-5-nano-medium-reasoning | 10s | $0.0002 | Inexpensive and moderately powerful. | | GPT-5-mini-high-reasoning | 20s | $0.002 | Very powerful and expensive. | | GPT-5-nano-high-reasoning | 20s | $0.0004 | Powerful. | ### Strategy Costs Strategies consume credits for every [event](/ai/events.md) they generate. The estimates below use GPT-4.1-mini and apply to each market. | Evaluation frequency | Events per market per day | Estimated credits per market per hour | | -------------------- | ------------------------: | ------------------------------------: | | 1s | 86,400 | $0.54 | | 5s | 17,280 | $0.108 | | 15s | 5,760 | $0.036 | | 30s | 2,880 | $0.018 | | 1m | 1,440 | $0.009 | | 3m | 480 | $0.003 | | 5m | 288 | $0.0018 | | 15m | 96 | $0.0006 | | 30m | 48 | $0.0003 | | 1h | 24 | $0.00015 |