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

# query

> Send a single query to an AI model and receive a single response

## Summary

Send a single query to an AI model and receive a single response. Unlike the `chat` command, this does not maintain conversational context and is ideal for one-off questions.

* Needs Admin: False
* Version: 0
* Author: @Ne0nd0g

### Arguments

#### provider

* Description: The model provider to interact with (Anthropic, Bedrock, OpenAI, ollama, OpenWebUI)
* Required: False (uses build parameters, user secrets, or environment variables if not specified)
* Type: Choose One
* Choices: Anthropic, Bedrock, OpenAI, ollama, OpenWebUI

#### model

* Description: The model to use for inference from the selected provider
* Required: False (uses build parameters, user secrets, or environment variables if not specified)
* Type: String

#### prompt

* Description: The prompt to send to the model for inference
* Required: True
* Type: String

#### tools

* Description: Use tools to enhance the model's capabilities
* Required: False
* Default: true
* Type: Boolean

#### verbose

* Description: Show verbose output of all user and AI messages
* Required: False
* Default: false
* Type: Boolean

#### API\_ENDPOINT

* Description: The API endpoint to use for the selected provider
* Required: False
* Type: String

#### API\_KEY

* Description: The API key to authenticate with the provider
* Required: False
* Type: String

#### AWS\_ACCESS\_KEY\_ID

* Description: AWS Access Key ID for Bedrock
* Required: False
* Type: String

#### AWS\_SECRET\_ACCESS\_KEY

* Description: AWS Secret Access Key for Bedrock
* Required: False
* Type: String

#### AWS\_SESSION\_TOKEN

* Description: AWS Session Token for Bedrock
* Required: False
* Type: String

#### AWS\_DEFAULT\_REGION

* Description: AWS Region for Bedrock
* Required: False
* Type: String

#### filename

* Description: The filename of an already uploaded file to send to the model
* Required: False
* Type: Choose One (dynamically populated)

#### file

* Description: Upload a new file to send to the model for analysis
* Required: False
* Type: File

## Usage

```
query -prompt "What is Kerberoasting?"
query -provider Anthropic -model claude-3-7-sonnet-latest -prompt "Explain Pass-the-Hash"
query -provider OpenAI -model gpt-4o-mini -prompt "List common persistence mechanisms"
query -prompt "Analyze this log" -file upload.log
```

## Detailed Summary

The `query` command sends a single prompt to an AI model and returns a single response. This is the most straightforward way to interact with AI models when you don't need conversational context.

### Use Cases

**Quick Information Retrieval**

* Look up technique details
* Get command syntax help
* Understand error messages

**One-Time Analysis**

* Analyze a single file or log
* Review a code snippet
* Check configuration settings

**Batch Operations**

* Send multiple independent queries
* Process different files separately
* Compare responses from different models

### File Support

The command supports two parameter groups for file handling:

**Default Group** - Use existing files

* Select from files already uploaded to Mythic
* Reference by filename parameter

**New File Group** - Upload new files

* Upload a file as part of the query
* Combine prompt with file analysis

### Tool Enhancement

When tools are enabled (default), models can:

* Access additional context from Mythic
* Perform structured analysis
* Generate formatted outputs
* Use specialized functions for better results

### Provider Comparison

**Anthropic Claude**

* Excellent for security analysis
* Strong reasoning capabilities
* Good at following instructions

**Bedrock Claude**

* Same Claude models via AWS
* Enterprise compliance features
* May have different rate limits

**OpenAI GPT**

* Fast response times
* Good general knowledge
* Wide ecosystem support

**ollama**

* Local model execution
* No API costs
* Privacy-focused option

### Performance Tips

* Keep prompts focused and specific
* Use tools for enhanced capabilities
* Match provider/model to task complexity
* Consider cost and speed trade-offs

<Info>
  Each query is independent. The model does not remember previous queries. For multi-turn conversations, use the `chat` command instead.
</Info>