Anthropic Messages

Creates a model response for the given chat conversation. This endpoint follows the Anthropic API specification and the requests are sent to the AWS Bedrock Anthropic endpoint.

To use the API you need an API key. Admins can create API keys in the settings.

All parameters from the Anthropic “Create a message” endpoint are supported according to the Anthropic specifications, with the following exception:

• model: The supported models are: claude-sonnet-4-5-20250929, claude-sonnet-4-20250514, claude-3-7-sonnet-20250219, claude-3-5-sonnet-20240620.

• The list of available models might differ if you are using your own API keys in Langdock (“Bring-your-own-keys / BYOK”, see https://docs.langdock.com/settings/models/byok). In that case, please reach out to your admin to understand which models are available in the API.

Authorization: API key required. Use the Authorization header as a Bearer token: Authorization: Bearer YOUR_API_KEY

---

Endpoint

POST https://api.langdock.com/anthropic/{region}/v1/messages

Path parameter:

• region (required) — enum: available options: eu, us

---

Example: cURL

curl

curl --request POST \
  --url https://api.langdock.com/anthropic/{region}/v1/messages \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "max_tokens": 1024,
  "messages": [
    {
      "content": "Write a haiku about cats.",
      "role": "user"
    }
  ],
  "model": "claude-sonnet-4-20250514"
}
'

Example successful response (200):

response.json

[
  {
    "content": [
      {
        "text": "Here is a haiku about cats:\n\nFeline grace and charm,\nPurring softly by the fire,\nCats reign supreme.",
        "type": "text"
      }
    ],
    "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
    "model": "claude-3-haiku-20240307",
    "role": "assistant",
    "stop_reason": "end_turn",
    "stop_sequence": null,
    "type": "message",
    "usage": {
      "input_tokens": 14,
      "output_tokens": 35
    }
  }
]

---

Rate limits

The rate limit for the Messages endpoint is 500 RPM (requests per minute) and 60.000 TPM (tokens per minute). Rate limits are defined at the workspace level — not at an API key level. Each model has its own rate limit. If you exceed your rate limit, you will receive a 429 Too Many Requests response. Rate limits are subject to change; refer to this documentation for the most up-to-date information.

If you need a higher rate limit, contact: [email protected]

---

Using Anthropic-compatible libraries

As the request and response format is the same as the Anthropic API, you can use libraries such as the Anthropic Python library (https://github.com/anthropics/anthropic-sdk-python) or the Vercel AI SDK (https://sdk.vercel.ai/docs/introduction) with the Langdock API.

Example using the Anthropic Python library

python

from anthropic import Anthropic
client = Anthropic(
  base_url="https://api.langdock.com/anthropic/eu/",
  api_key="<YOUR_LANGDOCK_API_KEY>"
)

message = client.messages.create(
  model="claude-3-haiku-20240307",
  messages=[
    { "role": "user", "content": "Write a haiku about cats" }
  ],
  max_tokens=1024,
)

print(message.content[0].text)

Example using the Vercel AI SDK in Node.js

node.js

import { generateText } from "ai";
import { createAnthropic } from "@ai-sdk/anthropic";

const langdockProvider = createAnthropic({
  baseURL: "https://api.langdock.com/anthropic/eu/v1",
  apiKey: "<YOUR_LANGDOCK_API_KEY>",
});

const result = await generateText({
  model: langdockProvider("claude-3-haiku-20240307"),
  prompt: "Write a haiku about cats",
});

console.log(result.text);

---

Request body (application/json)

All fields follow Anthropic's Messages API, with the supported models noted above.

• model (required) — enum: The model to complete your prompt.

  • Available: claude-sonnet-4-5-20250929, claude-sonnet-4-20250514, claude-3-7-sonnet-20250219, claude-3-5-sonnet-20240620

• messages (required) — array of InputMessage objects:

  • Each input message must be an object with role and content.

  • Roles: user, assistant

  • The first message must always use the user role.

  • content may be a string (shorthand for a single text block) or an array of content blocks with types (e.g., text, image).

  • Starting with Claude 3 models, image content blocks are supported using base64-encoded images:

    {"role":"user","content":[
      {"type":"image","source":{"type":"base64","media_type":"image/jpeg","data":"/9j/4AAQSkZJRg..."}},
      {"type":"text","text":"What is in this image?"}
    ]}

    Supported media types: image/jpeg, image/png, image/gif, image/webp.

• max_tokens (required) — integer: maximum number of tokens to generate. Range: x >= 1

• stop_sequences — array of strings: custom text sequences that will cause the model to stop generating.

• stream — boolean: whether to incrementally stream the response using server-sent events.

• system — string or array: system prompt (see Anthropic system prompts guide https://docs.anthropic.com/en/docs/system-prompts).

• temperature — number: randomness, default 1.0, range 0.0 to 1.0.

• tool_choice — object: how the model should use provided tools. Options include auto, any, tool.

• tools — array of tool definitions. Each tool includes:

  • name (required)

  • description (strongly recommended)

  • input_schema (required) — JSON schema describing the tool input shape. Tools allow the model to produce tool_use content blocks that you can execute and return results back as tool_result blocks.

• top_k — integer: sample only from top K options for each token (advanced use).

• top_p — number: nucleus sampling (0.0–1.0, advanced use).

(See Anthropic docs for additional examples and details: https://docs.anthropic.com/en/api/messages)

---

Response (200: application/json)

Returns a Message object. Key fields:

• id — string: unique object identifier.

• type — string: object type, always "message".

• role — string: conversational role, always "assistant".

• content — array of content blocks (e.g., {"type":"text","text":"Hi, I'm Claude."}).

• model — string: model used.

• stop_reason — enum: "end_turn", "max_tokens", "stop_sequence", "tool_use".

• stop_sequence — string: which custom stop sequence was generated (if any).

• usage — object: input_tokens, output_tokens (token counts).

Example content block:

[{"type":"text","text":"Hi! My name is Claude."}]

---

Tools and tool workflows

If you include tools in your request, the model may return tool_use content blocks representing the model's intended tool invocation. You can run those tools and optionally return results back to the model using tool_result content blocks.

Example tool definition and usage are available in the Anthropic docs (https://docs.anthropic.com/en/docs/tool-use).

---

Additional resources

• Anthropic API spec: https://docs.anthropic.com/en/api/messages

• Anthropic models overview: https://docs.anthropic.com/en/docs/models-overview

• Anthropic system prompts: https://docs.anthropic.com/en/docs/system-prompts

• Langdock BYOK settings: https://docs.langdock.com/settings/models/byok

Was this page helpful? (This line retained from original content.)