> ## Documentation Index
> Fetch the complete documentation index at: https://docs-v1.latitude.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Configuration

> Learn how to configure model, provider, and generation parameters for your prompts.

The configuration section, located at the top of every prompt file and enclosed by triple dashes (`---`), defines how Latitude executes your prompt. It's written in YAML format and allows you to specify the AI provider, model, generation parameters, and other advanced settings.

<img src="https://mintcdn.com/latitudellms/Ssq9dzRdSVyjHEcj/assets/prompt_config.png?fit=max&auto=format&n=Ssq9dzRdSVyjHEcj&q=85&s=9b1a324c1994b1a1d720b3d56734b976" alt="Prompt configuration section" width="1270" height="762" data-path="assets/prompt_config.png" />

```yaml theme={null}
---
provider: OpenAI
model: gpt-4o-mini
temperature: 0.6
top_p: 0.9
# ... other settings
---
```

<Note>
  Be sure there is a space after the colon ( : ) in your configurations.
</Note>

## Core Settings

### Provider (required)

Specifies the AI provider to use (e.g., OpenAI, Anthropic, Google). This must match a provider configured in your Latitude workspace settings.

You can easily select a configured provider using the dropdown in the editor's header.

<img src="https://mintcdn.com/latitudellms/Ssq9dzRdSVyjHEcj/assets/prompt_provider.png?fit=max&auto=format&n=Ssq9dzRdSVyjHEcj&q=85&s=8905518e3f02c4f8a58ef4b7a737e715" alt="Selecting a provider" width="1244" height="464" data-path="assets/prompt_provider.png" />

[Learn more about configuring providers](/guides/getting-started/providers).

### Model (required)

Specifies the exact language model to use (e.g., `gpt-4o-mini`, `claude-3-opus-20240229`). Available models depend on the selected provider.

The model dropdown in the editor's header lists available models for the chosen provider.

<img src="https://mintcdn.com/latitudellms/Ssq9dzRdSVyjHEcj/assets/prompt_model.png?fit=max&auto=format&n=Ssq9dzRdSVyjHEcj&q=85&s=643e9634e13678b2073d6d1a7a96ad4d" alt="Selecting a model" width="1276" height="436" data-path="assets/prompt_model.png" />

## Generation Parameters

These parameters control how the AI model generates its response. The specific ranges and behaviors might vary slightly between providers.

### `temperature`

Controls the randomness of the output. Lower values (e.g., 0.1) make the output more deterministic and focused, while higher values (e.g., 0.9) increase creativity and randomness.

<Note>
  Setting temperature to 0, or leaving it unset, enables response
  [caching](/guides/prompt-manager/cache) for identical inputs.
</Note>

It's generally recommended to adjust *either* `temperature` *or* `topP`, but not both.

### `maxTokens`

Sets the maximum number of tokens (words or parts of words) the model can generate in its response.

### `topP` (Nucleus Sampling)

An alternative to `temperature` for controlling randomness. It instructs the model to consider only the most probable tokens whose cumulative probability mass exceeds the `topP` value (e.g., 0.9 means consider tokens comprising the top 90% probability mass).

### `topK`

Restricts the model to sampling only from the `K` most likely next tokens at each step. Generally used for advanced cases; `temperature` or `topP` are usually sufficient.

### `presencePenalty`

Discourages the model from repeating information already present in the prompt context. Higher values increase the penalty.

### `frequencyPenalty`

Discourages the model from using the same words or phrases repeatedly in its response. Higher values increase the penalty.

### `stopSequences`

A list of strings that, if generated by the model, will cause generation to stop immediately.

### `seed`

An integer used to initialize the random number generator. If supported by the model, using the same seed with identical inputs will produce deterministic outputs, useful for reproducibility.

## Advanced Configuration

### `parameters`

Defines types and constraints for input parameters used in the [Playground](/guides/prompt-manager/playground) or shared prompts.

```yaml theme={null}
parameters:
  user_input:
    type: text # Default type
  image_upload:
    type: image
  data_file:
    type: file
```

[Learn more about parameter types in the Playground guide](/guides/prompt-manager/playground#parameter-types).

### `schema`

Defines a JSON schema to enforce structured output from the model.

[Learn more about enforcing JSON output](/guides/prompt-manager/json-output).

### `tools`

Lists the tools (functions) available for the AI model to call.

[Learn more about configuring tools](/guides/prompt-manager/tools).

### `maxSteps`

Sets the maximum number of execution steps allowed for your prompt (default: 20, max: 150). This prevents infinite loops and controls resource usage in [Chains](/promptl/advanced/chains) and [Agents](/guides/prompt-manager/agents).

**Automatic Application**: By default, Latitude automatically applies `maxSteps: 20` to all documents with configuration. This ensures safe execution limits for tool usage, chains, and multi-step operations.

**Opt-out Behavior**: A document is treated as a simple prompt (without `maxSteps` applied) in two cases:

1. **No configuration section** - Documents without frontmatter (no `---` delimiters)
2. **Explicit type declaration** - Setting `type: prompt` in the configuration

```yaml theme={null}
---
provider: OpenAI
model: gpt-4o-mini
type: prompt # Explicitly opt out of maxSteps behavior
---
```

You can also override the default by explicitly setting your own `maxSteps` value:

```yaml theme={null}
---
provider: OpenAI
model: gpt-4o-mini
maxSteps: 50 # Custom limit
---
```

### `maxRetries`

Maximum number of times to retry a provider call on failure (default: 2).

### `headers`

Sends additional HTTP headers with the request, useful for integrating with specific provider features or observability tools.

## Next Steps

* Test prompts with different settings in the [Playground](/guides/prompt-manager/playground)
* Learn about [Enforcing JSON Output](/guides/prompt-manager/json-output)
* Explore using [Tools](/guides/prompt-manager/tools) and [Agents](/guides/prompt-manager/agents)