> ## Documentation Index
> Fetch the complete documentation index at: https://wb-21fd5541-docs-2516.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# LLM

> TypeScript SDK reference

export const GitHubLink = ({url, compact = false}) => <a href={url} target="_blank" rel="noopener noreferrer" className={compact ? "source-link" : "github-source-link"}>
    {compact ? "View source" : <>
    <svg width="20" height="20" viewBox="0 0 24 24" fill="currentColor" xmlns="http://www.w3.org/2000/svg">
      <path d="M12 0C5.37 0 0 5.37 0 12c0 5.31 3.435 9.795 8.205 11.385.6.105.825-.255.825-.57 0-.285-.015-1.23-.015-2.235-3.015.555-3.795-.735-4.035-1.41-.135-.345-.72-1.41-1.23-1.695-.42-.225-1.02-.78-.015-.795.945-.015 1.62.87 1.845 1.23 1.08 1.815 2.805 1.305 3.495.99.105-.78.42-1.305.765-1.605-2.67-.3-5.46-1.335-5.46-5.925 0-1.305.465-2.385 1.23-3.225-.12-.3-.54-1.53.12-3.18 0 0 1.005-.315 3.3 1.23.96-.27 1.98-.405 3-.405s2.04.135 3 .405c2.295-1.56 3.3-1.23 3.3-1.23.66 1.65.24 2.88.12 3.18.765.84 1.23 1.905 1.23 3.225 0 4.605-2.805 5.625-5.475 5.925.435.375.81 1.095.81 2.22 0 1.605-.015 2.895-.015 3.3 0 .315.225.69.825.57A12.02 12.02 0 0024 12c0-6.63-5.37-12-12-12z" />
    </svg>
    GitHub source
      </>}
  </a>;

<GitHubLink url="https://github.com/wandb/weave/blob/7c9efdc9fe05ffcaf2430dd652ef9bc5b3ffdfaa/sdks/node/src/genai/llm.ts#L90" />

An LLM call. Emits a `chat` span with `gen_ai.*` attributes.

Created by `weave.startLLM()` (or `turn.startLLM()`) and terminated with
`end()`. Only one LLM may be active in an async context at a time; nest
tool/subagent calls under it via `startTool` / `startSubagent`.

Populate `inputMessages` / `outputMessages` / `usage` / `reasoning` directly,
or via the helper functions (`output`, `think`, `attachMedia`, `record`).

All recorded data is flushed to the span at `end()`.

## Examples

```ts twoslash theme={null}
// @noErrors
const llm = weave.startLLM({model: 'gpt-4o-mini', providerName: 'openai'});

try {
  llm.inputMessages = [{role: 'user', content: prompt}];
  const resp = await openai.chat.completions.create({...});
  llm.output(resp.choices[0].message.content ?? '');
  llm.record({usage: {inputTokens: resp.usage?.prompt_tokens}});
} finally {
  llm.end();
}
```

```ts twoslash theme={null}
// @noErrors
const llm = weave.startLLM({
  model: 'gpt-4o-mini',
  providerName: 'openai',
  systemInstructions: ['You are a helpful weather bot.'],
  startTime: new Date('2026-05-29T10:00:00.000Z'),
});

try {
  // ... call the LLM, populate llm.outputMessages / usage ...
} finally {
  llm.end();
}
```

## Extends

* `SpanBase`

## Properties

### inputMessages

> **inputMessages**: [`Message`](./message)\[] = `[]`

Input messages sent to the model. Flushed to `gen_ai.input.messages` on
`end()`.

***

### model

> `readonly` **model**: `string`

***

### outputMessages

> **outputMessages**: [`Message`](./message)\[] = `[]`

Assistant messages returned by the model. Flushed to
`gen_ai.output.messages` on `end()`.

***

### providerName

> `readonly` **providerName**: `string`

***

### reasoning

> `optional` **reasoning**: [`Reasoning`](./reasoning)

Chain-of-thought content. Folded into the last assistant message as a
ReasoningPart at serialization time.

***

### usage

> **usage**: [`Usage`](./usage) = `{}`

Token counts and cache stats. Flushed to `gen_ai.usage.*` on `end()`.

## Methods

### ~~addEvent()~~

<Warning>
  **Deprecated.** Record this data via [setAttributes](#setattributes) instead.
  OpenTelemetry is phasing out the Span Event API (`Span.addEvent`). This
  method still works and existing span-event data stays valid.
  See [https://opentelemetry.io/blog/2026/deprecating-span-events/](https://opentelemetry.io/blog/2026/deprecating-span-events/)
</Warning>

> **addEvent**(`name`, `attributes?`, `startTime?`): `this`

Add a named event to the span. Useful for marking non-span moments such as
context compaction, tool-loop detection, or guardrail trips. Warns and
no-ops after `end()`. Mirrors OTel `Span.addEvent`.

#### Parameters

<ParamField path="name" type="string" required />

<ParamField path="attributes" type="Attributes" />

<ParamField path="startTime" type="TimeInput" />

#### Returns

`this`

#### Example

```ts twoslash theme={null}
// @noErrors
span.addEvent('context_compacted', {removedMessages: 12});
```

#### Inherited from

`SpanBase.addEvent`

***

### attachMedia()

> **attachMedia**(`opts`): `this`

Stage a media attachment for the LLM call. Pick exactly one of
`content` (inline base64 bytes), `uri` (URI reference), or `fileId`
(pre-uploaded file id). The attachment is glued onto the last user
message in `inputMessages` on `end()`.

#### Parameters

<ParamField path="opts" type="{…} | {…} | {…}" required>
  See [`Modality`](../type-aliases/modality), [`Modality`](../type-aliases/modality), [`Modality`](../type-aliases/modality).

  Full type: `{ content: string; mimeType: string; modality: Modality; } | { modality: Modality; uri: string; } | { fileId: string; mimeType?: string; modality: Modality; }`
</ParamField>

#### Returns

`this`

***

### attachMediaUrl()

> **attachMediaUrl**(`url`, `opts`): `this`

Convenience for `attachMedia({uri, modality})`.

#### Parameters

<ParamField path="url" type="string" required />

<ParamField path="opts" type="object" required>
  <Expandable title="properties" defaultOpen>
    <ParamField path="modality" type="Modality" required>
      See [`Modality`](../type-aliases/modality).
    </ParamField>
  </Expandable>
</ParamField>

#### Returns

`this`

***

### end()

> **end**(`opts?`): `void`

Flush accumulated state and close the span. Idempotent. Pass `error` to mark failed; pass `endTime` to backdate the close.

#### Parameters

<ParamField path="opts" type="object">
  <Expandable title="properties" defaultOpen>
    <ParamField path="endTime" type="TimeInput" />

    <ParamField path="error" type="Error" />
  </Expandable>
</ParamField>

#### Returns

`void`

***

### output()

> **output**(`content`): `this`

Append an assistant message to the response.

#### Parameters

<ParamField path="content" type="string" required />

#### Returns

`this`

***

### record()

> **record**(`opts`): `this`

Bulk-set any subset of the mutable fields. Replaces (does not merge).
Useful for assigning everything at once after a provider call returns.

#### Parameters

<ParamField path="opts" type="object" required>
  <Expandable title="properties" defaultOpen>
    <ParamField path="finishReasons" type="string[]" />

    <ParamField path="inputMessages" type="Message[]">
      See [`Message`](./message).
    </ParamField>

    <ParamField path="mediaAttachments" type="({…} | {…} | {…})[]">
      See [`Modality`](../type-aliases/modality), [`Modality`](../type-aliases/modality), [`Modality`](../type-aliases/modality).

      Full type: `({ content: string; mimeType: string; modality: Modality; } | { modality: Modality; uri: string; } | { fileId: string; mimeType?: string; modality: Modality; })[]`
    </ParamField>

    <ParamField path="outputMessages" type="Message[]">
      See [`Message`](./message).
    </ParamField>

    <ParamField path="outputType" type="string" />

    <ParamField path="reasoning" type="Reasoning">
      See [`Reasoning`](./reasoning).
    </ParamField>

    <ParamField path="responseId" type="string" />

    <ParamField path="responseModel" type="string" />

    <ParamField path="usage" type="Usage">
      See [`Usage`](./usage).
    </ParamField>
  </Expandable>
</ParamField>

#### Returns

`this`

***

### setAttributes()

> **setAttributes**(`attributes`): `this`

Set multiple attributes on the span at once. Warns and no-ops after
`end()`. Mirrors OTel `Span.setAttributes` (and the Python SDK's
`set_attributes`).

#### Parameters

<ParamField path="attributes" type="Attributes" required />

#### Returns

`this`

#### Example

```ts twoslash theme={null}
// @noErrors
span.setAttributes({'weave.tag': 'prod', 'gen_ai.response.id': id});
```

#### Inherited from

`SpanBase.setAttributes`

***

### startSubagent()

> **startSubagent**(`opts`): [`SubAgent`](./subagent)

Start a child SubAgent span nested under this LLM.

#### Parameters

<ParamField path="opts" type="SubAgentInit" required>
  See [`SubAgentInit`](./subagentinit).
</ParamField>

#### Returns

[`SubAgent`](./subagent)

***

### startTool()

> **startTool**(`opts`): [`Tool`](./tool)

Start a child Tool span nested under this LLM.

#### Parameters

<ParamField path="opts" type="ToolInit" required>
  See [`ToolInit`](./toolinit).
</ParamField>

#### Returns

[`Tool`](./tool)

***

### think()

> **think**(`content`): `this`

Set or extend the model's reasoning/chain-of-thought content. Accumulates
into `this.reasoning.content`. Folded into the last assistant message as
a `ReasoningPart` at serialization time, matching the Python SDK's
on-the-wire shape.

#### Parameters

<ParamField path="content" type="string" required />

#### Returns

`this`