# ModelOutputLimit

> Tracon documentation. Tracon is a .NET package family that adds a control
> plane on Microsoft Agent Framework, published as NuGet packages that run
> inside your own ASP.NET Core application.
>
> Page: https://tracon.dev/api/tracon.modeloutputlimit/
> Summary: ModelOutputLimit: The output token limit a provider's chat client sends when ModelBinding.MaxOutputTokens is empty.

<div class="api-provenance">Namespace Tracon · Assembly <code>Tracon.Abstractions.dll</code></div>

The output token limit a provider's chat client sends when
[ModelBinding.MaxOutputTokens](/api/tracon.modelbinding/#Tracon_ModelBinding_MaxOutputTokens) is empty.

```csharp
public sealed record ModelOutputLimit : IEquatable<ModelOutputLimit>
```

<dl class="api-relations"><dt>Inheritance</dt><dd><a href="https://learn.microsoft.com/dotnet/api/system.object">object</a> ← <a href="/api/tracon.modeloutputlimit/">ModelOutputLimit</a></dd><dt>Implements</dt><dd><a href="https://learn.microsoft.com/dotnet/api/system.iequatable-1">IEquatable&lt;ModelOutputLimit&gt;</a></dd><dt>Inherited Members</dt><dd><a href="https://learn.microsoft.com/dotnet/api/system.object.gettype">object.GetType()</a>, <a href="https://learn.microsoft.com/dotnet/api/system.object.tostring">object.ToString()</a>, <a href="https://learn.microsoft.com/dotnet/api/system.object.equals#system-object-equals(system-object)">object.Equals(object?)</a>, <a href="https://learn.microsoft.com/dotnet/api/system.object.equals#system-object-equals(system-object-system-object)">object.Equals(object?, object?)</a>, <a href="https://learn.microsoft.com/dotnet/api/system.object.referenceequals">object.ReferenceEquals(object?, object?)</a>, <a href="https://learn.microsoft.com/dotnet/api/system.object.gethashcode">object.GetHashCode()</a></dd></dl>

## Remarks

A provider that sends its own default limit lets its raw chat client return
this record from `IChatClient.GetService(typeof(ModelOutputLimit))` —
the same way a client describes itself with `ChatClientMetadata`. The
client is built for one binding, so the record can depend on the binding's
provider settings. A provider that sends no limit (the model's own maximum
applies) returns nothing.

The agent validation report reads it. When the binding leaves
[ModelBinding.MaxOutputTokens](/api/tracon.modelbinding/#Tracon_ModelBinding_MaxOutputTokens) empty, the default is below the
model's [ModelDescriptor.MaxOutputTokens](/api/tracon.modeldescriptor/#Tracon_ModelDescriptor_MaxOutputTokens) in the catalog, and the
agent asks for a structured response or [ModelOutputLimit.HighReasoningEffort](/api/tracon.modeloutputlimit/#Tracon_ModelOutputLimit_HighReasoningEffort) is
[true](https://learn.microsoft.com/dotnet/csharp/language-reference/builtin-types/bool), the report carries a warning: a response cut off at
the limit fails a structured run ([RunErrorClass.OutputTruncated](/api/tracon.runerrorclass/)).

## Constructors

### <a id="Tracon_ModelOutputLimit__ctor"></a> ModelOutputLimit\(\)

```csharp
public ModelOutputLimit()
```

## Properties

### <a id="Tracon_ModelOutputLimit_DefaultMaxOutputTokens"></a> DefaultMaxOutputTokens

Gets the output token limit the client sends when the binding sets none.

```csharp
public required int DefaultMaxOutputTokens { get; init; }
```

#### Property Value

 [int](https://learn.microsoft.com/dotnet/api/system.int32)

### <a id="Tracon_ModelOutputLimit_HighReasoningEffort"></a> HighReasoningEffort

Gets a value indicating whether the binding asks the model to reason at high
effort, so reasoning tokens are likely to take a large share of the same limit.

```csharp
public bool HighReasoningEffort { get; init; }
```

#### Property Value

 [bool](https://learn.microsoft.com/dotnet/api/system.boolean)

## Methods

### <a id="Tracon_ModelOutputLimit_Equals_System_Object_"></a> Equals\(object?\)

```csharp
public override bool Equals(object? obj)
```

#### Parameters

`obj` [object](https://learn.microsoft.com/dotnet/api/system.object)?

#### Returns

 [bool](https://learn.microsoft.com/dotnet/api/system.boolean)

### <a id="Tracon_ModelOutputLimit_Equals_Tracon_ModelOutputLimit_"></a> Equals\(ModelOutputLimit?\)

```csharp
public bool Equals(ModelOutputLimit? other)
```

#### Parameters

`other` [ModelOutputLimit](/api/tracon.modeloutputlimit/)?

#### Returns

 [bool](https://learn.microsoft.com/dotnet/api/system.boolean)

### <a id="Tracon_ModelOutputLimit_GetHashCode"></a> GetHashCode\(\)

```csharp
public override int GetHashCode()
```

#### Returns

 [int](https://learn.microsoft.com/dotnet/api/system.int32)

### <a id="Tracon_ModelOutputLimit_ToString"></a> ToString\(\)

```csharp
public override string ToString()
```

#### Returns

 [string](https://learn.microsoft.com/dotnet/api/system.string)

## Operators

### <a id="Tracon_ModelOutputLimit_op_Equality_Tracon_ModelOutputLimit_Tracon_ModelOutputLimit_"></a> operator ==\(ModelOutputLimit?, ModelOutputLimit?\)

```csharp
public static bool operator ==(ModelOutputLimit? left, ModelOutputLimit? right)
```

#### Parameters

`left` [ModelOutputLimit](/api/tracon.modeloutputlimit/)?

`right` [ModelOutputLimit](/api/tracon.modeloutputlimit/)?

#### Returns

 [bool](https://learn.microsoft.com/dotnet/api/system.boolean)

### <a id="Tracon_ModelOutputLimit_op_Inequality_Tracon_ModelOutputLimit_Tracon_ModelOutputLimit_"></a> operator \!=\(ModelOutputLimit?, ModelOutputLimit?\)

```csharp
public static bool operator !=(ModelOutputLimit? left, ModelOutputLimit? right)
```

#### Parameters

`left` [ModelOutputLimit](/api/tracon.modeloutputlimit/)?

`right` [ModelOutputLimit](/api/tracon.modeloutputlimit/)?

#### Returns

 [bool](https://learn.microsoft.com/dotnet/api/system.boolean)