Class ChatAnthropic

import { ChatAnthropic } from '@langchain/anthropic';

const llm = new ChatAnthropic({
  model: "claude-sonnet-4-5-20250929",
  temperature: 0,
  maxTokens: undefined,
  maxRetries: 2,
  // apiKey: "...",
  // baseUrl: "...",
  // other params...
});
Copy

const input = `Translate "I love programming" into French.`;

// Models also accept a list of chat messages or a formatted prompt
const result = await llm.invoke(input);
console.log(result);
Copy

AIMessage {
  "id": "msg_01QDpd78JUHpRP6bRRNyzbW3",
  "content": "Here's the translation to French:\n\nJ'adore la programmation.",
  "response_metadata": {
    "id": "msg_01QDpd78JUHpRP6bRRNyzbW3",
    "model": "claude-sonnet-4-5-20250929",
    "stop_reason": "end_turn",
    "stop_sequence": null,
    "usage": {
      "input_tokens": 25,
      "output_tokens": 19
    },
    "type": "message",
    "role": "assistant"
  },
  "usage_metadata": {
    "input_tokens": 25,
    "output_tokens": 19,
    "total_tokens": 44
  }
}
Copy

for await (const chunk of await llm.stream(input)) {
  console.log(chunk);
}
Copy

AIMessageChunk {
  "id": "msg_01N8MwoYxiKo9w4chE4gXUs4",
  "content": "",
  "additional_kwargs": {
    "id": "msg_01N8MwoYxiKo9w4chE4gXUs4",
    "type": "message",
    "role": "assistant",
    "model": "claude-sonnet-4-5-20250929"
  },
  "usage_metadata": {
    "input_tokens": 25,
    "output_tokens": 1,
    "total_tokens": 26
  }
}
AIMessageChunk {
  "content": "",
}
AIMessageChunk {
  "content": "Here",
}
AIMessageChunk {
  "content": "'s",
}
AIMessageChunk {
  "content": " the translation to",
}
AIMessageChunk {
  "content": " French:\n\nJ",
}
AIMessageChunk {
  "content": "'adore la programmation",
}
AIMessageChunk {
  "content": ".",
}
AIMessageChunk {
  "content": "",
  "additional_kwargs": {
    "stop_reason": "end_turn",
    "stop_sequence": null
  },
  "usage_metadata": {
    "input_tokens": 0,
    "output_tokens": 19,
    "total_tokens": 19
  }
}
Copy

import { AIMessageChunk } from '@langchain/core/messages';
import { concat } from '@langchain/core/utils/stream';

const stream = await llm.stream(input);
let full: AIMessageChunk | undefined;
for await (const chunk of stream) {
  full = !full ? chunk : concat(full, chunk);
}
console.log(full);
Copy

AIMessageChunk {
  "id": "msg_01SBTb5zSGXfjUc7yQ8EKEEA",
  "content": "Here's the translation to French:\n\nJ'adore la programmation.",
  "additional_kwargs": {
    "id": "msg_01SBTb5zSGXfjUc7yQ8EKEEA",
    "type": "message",
    "role": "assistant",
    "model": "claude-sonnet-4-5-20250929",
    "stop_reason": "end_turn",
    "stop_sequence": null
  },
  "usage_metadata": {
    "input_tokens": 25,
    "output_tokens": 20,
    "total_tokens": 45
  }
}
Copy

import { z } from 'zod';

const GetWeather = {
  name: "GetWeather",
  description: "Get the current weather in a given location",
  schema: z.object({
    location: z.string().describe("The city and state, e.g. San Francisco, CA")
  }),
}

const GetPopulation = {
  name: "GetPopulation",
  description: "Get the current population in a given location",
  schema: z.object({
    location: z.string().describe("The city and state, e.g. San Francisco, CA")
  }),
}

const llmWithTools = llm.bindTools([GetWeather, GetPopulation]);
const aiMsg = await llmWithTools.invoke(
  "Which city is hotter today and which is bigger: LA or NY?"
);
console.log(aiMsg.tool_calls);
Copy

[
  {
    name: 'GetWeather',
    args: { location: 'Los Angeles, CA' },
    id: 'toolu_01WjW3Dann6BPJVtLhovdBD5',
    type: 'tool_call'
  },
  {
    name: 'GetWeather',
    args: { location: 'New York, NY' },
    id: 'toolu_01G6wfJgqi5zRmJomsmkyZXe',
    type: 'tool_call'
  },
  {
    name: 'GetPopulation',
    args: { location: 'Los Angeles, CA' },
    id: 'toolu_0165qYWBA2VFyUst5RA18zew',
    type: 'tool_call'
  },
  {
    name: 'GetPopulation',
    args: { location: 'New York, NY' },
    id: 'toolu_01PGNyP33vxr13tGqr7i3rDo',
    type: 'tool_call'
  }
]
Copy

Tool search enables Claude to dynamically discover and load tools on-demand instead of loading all tool definitions upfront. This is useful when you have many tools but want to avoid the overhead of sending all definitions with every request.

import { ChatAnthropic } from "@langchain/anthropic";

const model = new ChatAnthropic({
  model: "claude-sonnet-4-5-20250929",
});

const tools = [
  // Tool search server tool
  {
    type: "tool_search_tool_regex_20251119",
    name: "tool_search_tool_regex",
  },
  // Tools with defer_loading are loaded on-demand
  {
    name: "get_weather",
    description: "Get the current weather for a location",
    input_schema: {
      type: "object",
      properties: {
        location: { type: "string", description: "City name" },
        unit: {
          type: "string",
          enum: ["celsius", "fahrenheit"],
        },
      },
      required: ["location"],
    },
    defer_loading: true, // Tool is loaded on-demand
  },
  {
    name: "search_files",
    description: "Search through files in the workspace",
    input_schema: {
      type: "object",
      properties: {
        query: { type: "string" },
      },
      required: ["query"],
    },
    defer_loading: true, // Tool is loaded on-demand
  },
];

const modelWithTools = model.bindTools(tools);
const response = await modelWithTools.invoke("What's the weather in San Francisco?");
Copy

You can also use the tool() helper with the extras field:

import { tool } from "@langchain/core/tools";
import { z } from "zod";

const getWeather = tool(
  async (input) => `Weather in ${input.location}`,
  {
    name: "get_weather",
    description: "Get weather for a location",
    schema: z.object({ location: z.string() }),
    extras: { defer_loading: true },
  }
);
Copy

Note: The required advanced-tool-use-2025-11-20 beta header is automatically appended to the request when using tool search tools.

Best practices:

• Tools with defer_loading: true are only loaded when Claude discovers them via search
• Keep your 3-5 most frequently used tools as non-deferred for optimal performance
• Both regex and bm25 variants search tool names, descriptions, and argument info

See the Claude docs for more information.

ChatAnthropic supports structured output through two main approaches:

1. Function Calling with withStructuredOutput(): Uses Anthropic's tool calling under the hood to constrain outputs to a specific schema.
2. JSON Schema Mode: Uses Anthropic's native JSON schema support for direct structured output without tool calling overhead.

Using withStructuredOutput (Function Calling)

This method leverages Anthropic's tool calling capabilities to ensure the model returns data matching your schema:

import { z } from 'zod';

const Joke = z.object({
  setup: z.string().describe("The setup of the joke"),
  punchline: z.string().describe("The punchline to the joke"),
  rating: z.number().optional().describe("How funny the joke is, from 1 to 10")
}).describe('Joke to tell user.');

const structuredLlm = llm.withStructuredOutput(Joke, { name: "Joke" });
const jokeResult = await structuredLlm.invoke("Tell me a joke about cats");
console.log(jokeResult);
Copy

{
  setup: "Why don't cats play poker in the jungle?",
  punchline: 'Too many cheetahs!',
  rating: 7
}
Copy

Using JSON Schema Mode

For more direct control, you can use Anthropic's native JSON schema support by passing method: "jsonSchema":

import { z } from 'zod';

const RecipeSchema = z.object({
  recipeName: z.string().describe("Name of the recipe"),
  ingredients: z.array(z.string()).describe("List of ingredients needed"),
  steps: z.array(z.string()).describe("Cooking steps in order"),
  prepTime: z.number().describe("Preparation time in minutes")
});

const structuredLlm = llm.withStructuredOutput(RecipeSchema, {
  method: "jsonSchema"
});

const recipe = await structuredLlm.invoke(
  "Give me a simple recipe for chocolate chip cookies"
);
console.log(recipe);
Copy

{
  recipeName: 'Classic Chocolate Chip Cookies',
  ingredients: [
    '2 1/4 cups all-purpose flour',
    '1 cup butter, softened',
    ...
  ],
  steps: [
    'Preheat oven to 375°F',
    'Mix butter and sugars until creamy',
    ...
  ],
  prepTime: 15
}
Copy

import { HumanMessage } from '@langchain/core/messages';

const imageUrl = "https://example.com/image.jpg";
const imageData = await fetch(imageUrl).then(res => res.arrayBuffer());
const base64Image = Buffer.from(imageData).toString('base64');

const message = new HumanMessage({
  content: [
    { type: "text", text: "describe the weather in this image" },
    {
      type: "image_url",
      image_url: { url: `data:image/jpeg;base64,${base64Image}` },
    },
  ]
});

const imageDescriptionAiMsg = await llm.invoke([message]);
console.log(imageDescriptionAiMsg.content);
Copy

The weather in this image appears to be beautiful and clear. The sky is a vibrant blue with scattered white clouds, suggesting a sunny and pleasant day. The clouds are wispy and light, indicating calm conditions without any signs of storms or heavy weather. The bright green grass on the rolling hills looks lush and well-watered, which could mean recent rainfall or good growing conditions. Overall, the scene depicts a perfect spring or early summer day with mild temperatures, plenty of sunshine, and gentle breezes - ideal weather for enjoying the outdoors or for plant growth.
Copy

const aiMsgForMetadata = await llm.invoke(input);
console.log(aiMsgForMetadata.usage_metadata);
Copy

{ input_tokens: 25, output_tokens: 19, total_tokens: 44 }
Copy

const streamForMetadata = await llm.stream(
  input,
  {
    streamUsage: true
  }
);
let fullForMetadata: AIMessageChunk | undefined;
for await (const chunk of streamForMetadata) {
  fullForMetadata = !fullForMetadata ? chunk : concat(fullForMetadata, chunk);
}
console.log(fullForMetadata?.usage_metadata);
Copy

{ input_tokens: 25, output_tokens: 20, total_tokens: 45 }
Copy

const aiMsgForResponseMetadata = await llm.invoke(input);
console.log(aiMsgForResponseMetadata.response_metadata);
Copy

{
  id: 'msg_01STxeQxJmp4sCSpioD6vK3L',
  model: 'claude-sonnet-4-5-20250929',
  stop_reason: 'end_turn',
  stop_sequence: null,
  usage: { input_tokens: 25, output_tokens: 19 },
  type: 'message',
  role: 'assistant'
}
Copy