Messages ↗

Original Documentation

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

Messages are the fundamental unit of context for models in LangChain. They represent the input and output of models, carrying both the content and metadata needed to represent the state of a conversation when interacting with an LLM.

Messages are objects that contain:

Role - Identifies the message type (e.g. system, user)
Content - Represents the actual content of the message (like text, images, audio, documents, etc.)
Metadata - Optional fields such as response information, message IDs, and token usage

LangChain provides a standard message type that works across all model providers, ensuring consistent behavior regardless of the model being called.

Basic usage#

The simplest way to use messages is to create message objects and pass them to a model when invoking.


const model = await initChatModel("gpt-5-nano");

const systemMsg = new SystemMessage("You are a helpful assistant.");
const humanMsg = new HumanMessage("Hello, how are you?");

const messages = [systemMsg, humanMsg];
const response = await model.invoke(messages);  // Returns AIMessage

Text prompts#

Text prompts are strings - ideal for straightforward generation tasks where you don’t need to retain conversation history.

const response = await model.invoke("Write a haiku about spring");

Use text prompts when:

You have a single, standalone request
You don’t need conversation history
You want minimal code complexity

Message prompts#

Alternatively, you can pass in a list of messages to the model by providing a list of message objects.


const messages = [
  new SystemMessage("You are a poetry expert"),
  new HumanMessage("Write a haiku about spring"),
  new AIMessage("Cherry blossoms bloom..."),
];
const response = await model.invoke(messages);

Use message prompts when:

Managing multi-turn conversations
Working with multimodal content (images, audio, files)
Including system instructions

Dictionary format#

You can also specify messages directly in OpenAI chat completions format.

const messages = [
  { role: "system", content: "You are a poetry expert" },
  { role: "user", content: "Write a haiku about spring" },
  { role: "assistant", content: "Cherry blossoms bloom..." },
];
const response = await model.invoke(messages);

Message types#

System message - Tells the model how to behave and provide context for interactions
Human message - Represents user input and interactions with the model
AI message - Responses generated by the model, including text content, tool calls, and metadata
Tool message - Represents the outputs of tool calls

System message#

A SystemMessage represent an initial set of instructions that primes the model’s behavior. You can use a system message to set the tone, define the model’s role, and establish guidelines for responses.


const systemMsg = new SystemMessage("You are a helpful coding assistant.");

const messages = [
  systemMsg,
  new HumanMessage("How do I create a REST API?"),
];
const response = await model.invoke(messages);


const systemMsg = new SystemMessage(`
You are a senior TypeScript developer with expertise in web frameworks.
Always provide code examples and explain your reasoning.
Be concise but thorough in your explanations.
`);

const messages = [
  systemMsg,
  new HumanMessage("How do I create a REST API?"),
];
const response = await model.invoke(messages);

Human message#

A HumanMessage represents user input and interactions. They can contain text, images, audio, files, and any other amount of multimodal content.

Text content#

const response = await model.invoke([
  new HumanMessage("What is machine learning?"),
]);

const response = await model.invoke("What is machine learning?");

Message metadata#

const humanMsg = new HumanMessage({
  content: "Hello!",
  name: "alice",
  id: "msg_123",
});

The name field behavior varies by provider – some use it for user identification, others ignore it. To check, refer to the model provider’s reference.

AI message#

An AIMessage represents the output of a model invocation. They can include multimodal data, tool calls, and provider-specific metadata that you can later access.

const response = await model.invoke("Explain AI");
console.log(typeof response);  // AIMessage

AIMessage objects are returned by the model when calling it, which contains all of the associated metadata in the response.

Providers weigh/contextualize types of messages differently, which means it is sometimes helpful to manually create a new AIMessage object and insert it into the message history as if it came from the model.


const aiMsg = new AIMessage("I'd be happy to help you with that question!");

const messages = [
  new SystemMessage("You are a helpful assistant"),
  new HumanMessage("Can you help me?"),
  aiMsg,  // Insert as if it came from the model
  new HumanMessage("Great! What's 2+2?")
]

const response = await model.invoke(messages);

The text content of the message. The raw content of the message. The standardized content blocks of the message. (See [content](#message-content)) The tool calls made by the model.

Empty if no tools are called.

A unique identifier for the message (either automatically generated by LangChain or returned in the provider response) The usage metadata of the message, which can contain token counts when available. See [`UsageMetadata`](https://reference.langchain.com/javascript/langchain-core/messages/UsageMetadata). The response metadata of the message.

Tool calls#

When models make tool calls, they’re included in the AIMessage:

const modelWithTools = model.bindTools([getWeather]);
const response = await modelWithTools.invoke("What's the weather in Paris?");

for (const toolCall of response.tool_calls) {
  console.log(`Tool: ${toolCall.name}`);
  console.log(`Args: ${toolCall.args}`);
  console.log(`ID: ${toolCall.id}`);
}

Other structured data, such as reasoning or citations, can also appear in message content.

Token usage#

An AIMessage can hold token counts and other usage metadata in its usage_metadata field:


const model = await initChatModel("gpt-5-nano");

const response = await model.invoke("Hello!");
console.log(response.usage_metadata);

{
  "output_tokens": 304,
  "input_tokens": 8,
  "total_tokens": 312,
  "input_token_details": {
    "cache_read": 0
  },
  "output_token_details": {
    "reasoning": 256
  }
}

See UsageMetadata for details.

Streaming and chunks#

During streaming, you’ll receive AIMessageChunk objects that can be combined into a full message object:

import { AIMessageChunk } from "langchain";

let finalChunk: AIMessageChunk | undefined;
for (const chunk of chunks) {
  finalChunk = finalChunk ? finalChunk.concat(chunk) : chunk;
}

Learn more:

Tool message#

For models that support tool calling, AI messages can contain tool calls. Tool messages are used to pass the results of a single tool execution back to the model.

Tools can generate ToolMessage objects directly. Below, we show a simple example. Read more in the tools guide.


const aiMessage = new AIMessage({
  content: [],
  tool_calls: [{
    name: "get_weather",
    args: { location: "San Francisco" },
    id: "call_123"
  }]
});

const toolMessage = new ToolMessage({
  content: "Sunny, 72°F",
  tool_call_id: "call_123"
});

const messages = [
  new HumanMessage("What's the weather in San Francisco?"),
  aiMessage,  // Model's tool call
  toolMessage,  // Tool execution result
];

const response = await model.invoke(messages);  // Model processes the result

The stringified output of the tool call. The ID of the tool call that this message is responding to. Must match the ID of the tool call in the [`AIMessage`](https://reference.langchain.com/javascript/langchain-core/messages/AIMessage). The name of the tool that was called. Additional data not sent to the model but can be accessed programmatically.

The artifact field stores supplementary data that won’t be sent to the model but can be accessed programmatically. This is useful for storing raw results, debugging information, or data for downstream processing without cluttering the model’s context.

For example, a [retrieval](/oss/javascript/langchain/retrieval) tool could retrieve a passage from a document for reference by a model. Where message `content` contains text that the model will reference, an `artifact` can contain document identifiers or other metadata that an application can use (e.g., to render a page). See example below:

    import { ToolMessage } from "langchain";

    // Artifact available downstream
    const artifact = { document_id: "doc_123", page: 0 };

    const toolMessage = new ToolMessage({
      content: "It was the best of times, it was the worst of times.",
      tool_call_id: "call_123",
      name: "search_books",
      artifact
    });
    ```

See the [RAG tutorial](/oss/javascript/langchain/rag) for an end-to-end example of building retrieval [agents](/oss/javascript/langchain/agents) with LangChain.
  </Accordion>
<span class="callout-end"></span>

***

## Message content

You can think of a message's content as the payload of data that gets sent to the model. Messages have a `content` attribute that is loosely-typed, supporting strings and lists of untyped objects (e.g., dictionaries). This allows support for provider-native structures directly in LangChain chat models, such as [multimodal](#multimodal) content and other data.

Separately, LangChain provides dedicated content types for text, reasoning, citations, multi-modal data, server-side tool calls, and other message content. See [content blocks](#standard-content-blocks) below.

LangChain chat models accept message content in the `content` attribute.

This may contain either:

1. A string
2. A list of content blocks in a provider-native format
3. A list of [LangChain's standard content blocks](#standard-content-blocks)

See below for an example using [multimodal](#multimodal) inputs:

```typescript

// String content
const humanMessage = new HumanMessage("Hello, how are you?");

// Provider-native format (e.g., OpenAI)
const humanMessage = new HumanMessage({
  content: [
    { type: "text", text: "Hello, how are you?" },
    {
      type: "image_url",
      image_url: { url: "https://example.com/image.jpg" },
    },
  ],
});

// List of standard content blocks
const humanMessage = new HumanMessage({
  contentBlocks: [
    { type: "text", text: "Hello, how are you?" },
    { type: "image", url: "https://example.com/image.jpg" },
  ],
});

Standard content blocks#

LangChain provides a standard representation for message content that works across providers.

Message objects implement a contentBlocks property that will lazily parse the content attribute into a standard, type-safe representation. For example, messages generated from ChatAnthropic or ChatOpenAI will include thinking or reasoning blocks in the format of the respective provider, but can be lazily parsed into a consistent ReasoningContentBlock representation:

    import { AIMessage } from "@langchain/core/messages";

    const message = new AIMessage({
      content: [
        {
          "type": "thinking",
          "thinking": "...",
          "signature": "WaUjzkyp...",
        },
        {
          "type":"text",
          "text": "...",
          "id": "msg_abc123",
        },
      ],
      response_metadata: { model_provider: "anthropic" },
    });

    console.log(message.contentBlocks);
    ```
  <span class="tab-end"></span>

  <span class="tab-start" data-tab-title="OpenAI"></span>
```typescript
    import { AIMessage } from "@langchain/core/messages";

    const message = new AIMessage({
      content: [
        {
          "type": "reasoning",
          "id": "rs_abc123",
          "summary": [
            {"type": "summary_text", "text": "summary 1"},
            {"type": "summary_text", "text": "summary 2"},
          ],
        },
        {"type": "text", "text": "..."},
      ],
      response_metadata: { model_provider: "openai" },
    });

    console.log(message.contentBlocks);
    ```
  <span class="tab-end"></span>
<span class="tab-group-end"></span>

See the [integrations guides](/oss/javascript/integrations/providers/overview) to get started with the
inference provider of your choice.

<span class="callout-start" data-callout-type="note"></span>
  **Serializing standard content**

  If an application outside of LangChain needs access to the standard content block
  representation, you can opt-in to storing content blocks in message content.

  To do this, you can set the `LC_OUTPUT_VERSION` environment variable to `v1`. Or,
  initialize any chat model with `outputVersion: "v1"`:

  ```typescript
  import { initChatModel } from "langchain";

  const model = await initChatModel(
    "gpt-5-nano",
    { outputVersion: "v1" }
  );

Multimodal#

Multimodality refers to the ability to work with data that comes in different forms, such as text, audio, images, and video. LangChain includes standard types for these data that can be used across providers.

Chat models can accept multimodal data as input and generate it as output. Below we show short examples of input messages featuring multimodal data.

Extra keys can be included top-level in the content block or nested in "extras": {"key": value}.

OpenAI and AWS Bedrock Converse, for example, require a filename for PDFs. See the provider page for your chosen model for specifics.

// From URL
const message = new HumanMessage({
  content: [
    { type: "text", text: "Describe the content of this image." },
    {
      type: "image",
      source_type: "url",
      url: "https://example.com/path/to/image.jpg"
    },
  ],
});

// From base64 data
const message = new HumanMessage({
  content: [
    { type: "text", text: "Describe the content of this image." },
    {
      type: "image",
      source_type: "base64",
      data: "AAAAIGZ0eXBtcDQyAAAAAGlzb21tcDQyAAACAGlzb2...",
    },
  ],
});

// From provider-managed File ID
const message = new HumanMessage({
  content: [
    { type: "text", text: "Describe the content of this image." },
    { type: "image", source_type: "id", id: "file-abc123" },
  ],
});

// From URL
const message = new HumanMessage({
  content: [
    { type: "text", text: "Describe the content of this document." },
    { type: "file", source_type: "url", url: "https://example.com/path/to/document.pdf", mime_type: "application/pdf" },
  ],
});

// From base64 data
const message = new HumanMessage({
  content: [
    { type: "text", text: "Describe the content of this document." },
    {
      type: "file",
      source_type: "base64",
      data: "AAAAIGZ0eXBtcDQyAAAAAGlzb21tcDQyAAACAGlzb2...",
      mime_type: "application/pdf",
    },
  ],
});

// From provider-managed File ID
const message = new HumanMessage({
  content: [
    { type: "text", text: "Describe the content of this document." },
    { type: "file", source_type: "id", id: "file-abc123" },
  ],
});

// From base64 data
const message = new HumanMessage({
  content: [
    { type: "text", text: "Describe the content of this audio." },
    {
      type: "audio",
      source_type: "base64",
      data: "AAAAIGZ0eXBtcDQyAAAAAGlzb21tcDQyAAACAGlzb2...",
    },
  ],
});

// From provider-managed File ID
const message = new HumanMessage({
  content: [
    { type: "text", text: "Describe the content of this audio." },
    { type: "audio", source_type: "id", id: "file-abc123" },
  ],
});

// From base64 data
const message = new HumanMessage({
  content: [
    { type: "text", text: "Describe the content of this video." },
    {
      type: "video",
      source_type: "base64",
      data: "AAAAIGZ0eXBtcDQyAAAAAGlzb21tcDQyAAACAGlzb2...",
    },
  ],
});

// From provider-managed File ID
const message = new HumanMessage({
  content: [
    { type: "text", text: "Describe the content of this video." },
    { type: "video", source_type: "id", id: "file-abc123" },
  ],
});

Not all models support all file types. Check the model provider’s reference for supported formats and size limits.

Content block reference#

Content blocks are represented (either when creating a message or accessing the contentBlocks field) as a list of typed objects. Each item in the list must adhere to one of the following block types:

**Purpose:** Standard text output

<ParamField body="type" type="string" required>
  Always `"text"`
</ParamField>

<ParamField body="text" type="string" required>
  The text content
</ParamField>

<ParamField body="annotations" type="Citation[]">
  List of annotations for the text
</ParamField>

**Example:**

```typescript
    {
        type: "text",
        text: "Hello world",
        annotations: []
    }
    ```

**Purpose:** Model reasoning steps

<ParamField body="type" type="string" required>
  Always `"reasoning"`
</ParamField>

<ParamField body="reasoning" type="string" required>
  The reasoning content
</ParamField>

**Example:**

```typescript
    {
        type: "reasoning",
        reasoning: "The user is asking about..."
    }
    ```

**Purpose:** Image data

<ParamField body="type" type="string" required>
  Always `"image"`
</ParamField>

<ParamField body="url" type="string">
  URL pointing to the image location.
</ParamField>

<ParamField body="data" type="string">
  Base64-encoded image data.
</ParamField>

<ParamField body="fileId" type="string">
  Reference to the image in an external file storage system (e.g., OpenAI or Anthropic's Files API).
</ParamField>

<ParamField body="mimeType" type="string">
  Image [MIME type](https://www.iana.org/assignments/media-types/media-types.xhtml#image) (e.g., `image/jpeg`, `image/png`). Required for base64 data.
</ParamField>

**Purpose:** Audio data

<ParamField body="type" type="string" required>
  Always `"audio"`
</ParamField>

<ParamField body="url" type="string">
  URL pointing to the audio location.
</ParamField>

<ParamField body="data" type="string">
  Base64-encoded audio data.
</ParamField>

<ParamField body="fileId" type="string">
  Reference to the audio file in an external file storage system (e.g., OpenAI or Anthropic's Files API).
</ParamField>

<ParamField body="mimeType" type="string">
  Audio [MIME type](https://www.iana.org/assignments/media-types/media-types.xhtml#audio) (e.g., `audio/mpeg`, `audio/wav`). Required for base64 data.
</ParamField>

**Purpose:** Video data

<ParamField body="type" type="string" required>
  Always `"video"`
</ParamField>

<ParamField body="url" type="string">
  URL pointing to the video location.
</ParamField>

<ParamField body="data" type="string">
  Base64-encoded video data.
</ParamField>

<ParamField body="fileId" type="string">
  Reference to the video file in an external file storage system (e.g., OpenAI or Anthropic's Files API).
</ParamField>

<ParamField body="mimeType" type="string">
  Video [MIME type](https://www.iana.org/assignments/media-types/media-types.xhtml#video) (e.g., `video/mp4`, `video/webm`). Required for base64 data.
</ParamField>

**Purpose:** Generic files (PDF, etc)

<ParamField body="type" type="string" required>
  Always `"file"`
</ParamField>

<ParamField body="url" type="string">
  URL pointing to the file location.
</ParamField>

<ParamField body="data" type="string">
  Base64-encoded file data.
</ParamField>

<ParamField body="fileId" type="string">
  Reference to the file in an external file storage system (e.g., OpenAI or Anthropic's Files API).
</ParamField>

<ParamField body="mimeType" type="string">
  File [MIME type](https://www.iana.org/assignments/media-types/media-types.xhtml) (e.g., `application/pdf`). Required for base64 data.
</ParamField>

**Purpose:** Document text (`.txt`, `.md`)

<ParamField body="type" type="string" required>
  Always `"text-plain"`
</ParamField>

<ParamField body="text" type="string" required>
  The text content
</ParamField>

<ParamField body="title" type="string">
  Title of the text content
</ParamField>

<ParamField body="mimeType" type="string">
  [MIME type](https://www.iana.org/assignments/media-types/media-types.xhtml) of the text (e.g., `text/plain`, `text/markdown`)
</ParamField>

**Purpose:** Function calls

<ParamField body="type" type="string" required>
  Always `"tool_call"`
</ParamField>

<ParamField body="name" type="string" required>
  Name of the tool to call
</ParamField>

<ParamField body="args" type="object" required>
  Arguments to pass to the tool
</ParamField>

<ParamField body="id" type="string" required>
  Unique identifier for this tool call
</ParamField>

**Example:**

```typescript
    {
        type: "tool_call",
        name: "search",
        args: { query: "weather" },
        id: "call_123"
    }
    ```

**Purpose:** Streaming tool fragments

<ParamField body="type" type="string" required>
  Always `"tool_call_chunk"`
</ParamField>

<ParamField body="name" type="string">
  Name of the tool being called
</ParamField>

<ParamField body="args" type="string">
  Partial tool arguments (may be incomplete JSON)
</ParamField>

<ParamField body="id" type="string">
  Tool call identifier
</ParamField>

<ParamField body="index" type="number | string" required>
  Position of this chunk in the stream
</ParamField>

**Purpose:** Malformed calls

<ParamField body="type" type="string" required>
  Always `"invalid_tool_call"`
</ParamField>

<ParamField body="name" type="string">
  Name of the tool that failed to be called
</ParamField>

<ParamField body="args" type="string">
  Raw arguments that failed to parse
</ParamField>

<ParamField body="error" type="string" required>
  Description of what went wrong
</ParamField>

**Common errors:** Invalid JSON, missing required fields

**Purpose:** Tool call that is executed server-side.

<ParamField body="type" type="string" required>
  Always `"server_tool_call"`
</ParamField>

<ParamField body="id" type="string" required>
  An identifier associated with the tool call.
</ParamField>

<ParamField body="name" type="string" required>
  The name of the tool to be called.
</ParamField>

<ParamField body="args" type="string" required>
  Partial tool arguments (may be incomplete JSON)
</ParamField>

**Purpose:** Streaming server-side tool call fragments

<ParamField body="type" type="string" required>
  Always `"server_tool_call_chunk"`
</ParamField>

<ParamField body="id" type="string">
  An identifier associated with the tool call.
</ParamField>

<ParamField body="name" type="string">
  Name of the tool being called
</ParamField>

<ParamField body="args" type="string">
  Partial tool arguments (may be incomplete JSON)
</ParamField>

<ParamField body="index" type="number | string">
  Position of this chunk in the stream
</ParamField>

**Purpose:** Search results

<ParamField body="type" type="string" required>
  Always `"server_tool_result"`
</ParamField>

<ParamField body="tool_call_id" type="string" required>
  Identifier of the corresponding server tool call.
</ParamField>

<ParamField body="id" type="string">
  Identifier associated with the server tool result.
</ParamField>

<ParamField body="status" type="string" required>
  Execution status of the server-side tool. `"success"` or `"error"`.
</ParamField>

<ParamField body="output">
  Output of the executed tool.
</ParamField>

**Purpose:** Provider-specific escape hatch Always `"non_standard"` Provider-specific data structure

Usage: For experimental or provider-unique features

Additional provider-specific content types may be found within the reference documentation of each model provider.

Each of these content blocks mentioned above are indvidually addressable as types when importing the ContentBlock type.


// Text block
const textBlock: ContentBlock.Text = {
    type: "text",
    text: "Hello world",
}

// Image block
const imageBlock: ContentBlock.Multimodal.Image = {
    type: "image",
    url: "https://example.com/image.png",
    mimeType: "image/png",
}

View the canonical type definitions in the API reference.

Content blocks were introduced as a new property on messages in LangChain v1 to standardize content formats across providers while maintaining backward compatibility with existing code.

Content blocks are not a replacement for the content property, but rather a new property that can be used to access the content of a message in a standardized format.

Use with chat models#

Chat models accept a sequence of message objects as input and return an AIMessage as output. Interactions are often stateless, so that a simple conversational loop involves invoking a model with a growing list of messages.

Refer to the below guides to learn more:

Built-in features for persisting and managing conversation histories
Strategies for managing context windows, including trimming and summarizing messages

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Link last verified June 7, 2026. View original ↗

Source: LangChain Docs

Link last verified: 2026-03-04