Anthropic Chat Format (Messages)

Official Documentation

Anthropic Messages

📝 Introduction

All Claude models on the gateway can be called natively via the Anthropic Messages API format. This is the recommended format when using the official Anthropic SDKs or tools like Claude Code.

📮 Endpoint

POST /v1/messages

Authentication

Anthropic-style headers are used:

x-api-key: $WS_API_KEY
anthropic-version: 2023-06-01

The Authorization: Bearer $WS_API_KEY header is also accepted.

💡 Request Examples

Basic Chat ✅

curl http://baseurl/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $WS_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello, Claude!"}
    ]
  }'

Response Example:

{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  "model": "claude-sonnet-4-6",
  "content": [
    {"type": "text", "text": "Hello! How can I help you today?"}
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 10,
    "output_tokens": 12
  }
}

System Prompt ✅

curl http://baseurl/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $WS_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-haiku-4-5-20251001",
    "max_tokens": 1024,
    "system": "You are a professional translator. Translate everything to Arabic.",
    "messages": [
      {"role": "user", "content": "Good morning!"}
    ]
  }'

Streaming Response ✅

curl http://baseurl/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $WS_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "stream": true,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Streaming events:

event: message_start
data: {"type":"message_start","message":{"id":"msg_...","type":"message","role":"assistant","content":[],"model":"claude-sonnet-4-6","usage":{"input_tokens":10}}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello"}}

event: message_stop
data: {"type":"message_stop"}

Image Input ✅

curl http://baseurl/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $WS_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "image",
            "source": {"type": "url", "url": "https://example.com/photo.jpg"}
          },
          {"type": "text", "text": "Describe this image."}
        ]
      }
    ]
  }'

Base64 is also supported: "source": {"type": "base64", "media_type": "image/jpeg", "data": "..."}.

Tool Use ✅

curl http://baseurl/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $WS_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-opus-4-8",
    "max_tokens": 1024,
    "tools": [
      {
        "name": "get_weather",
        "description": "Get the current weather for a given location",
        "input_schema": {
          "type": "object",
          "properties": {
            "location": {"type": "string", "description": "City name"}
          },
          "required": ["location"]
        }
      }
    ],
    "messages": [
      {"role": "user", "content": "What is the weather in Riyadh?"}
    ]
  }'

Response Example:

{
  "id": "msg_01Aq9w938a90dw8q",
  "type": "message",
  "role": "assistant",
  "model": "claude-opus-4-8",
  "content": [
    {
      "type": "tool_use",
      "id": "toolu_01A09q90qw90lq917835lq9",
      "name": "get_weather",
      "input": {"location": "Riyadh"}
    }
  ],
  "stop_reason": "tool_use"
}

Using the Official SDK

import anthropic

client = anthropic.Anthropic(
    api_key="sk-...",                     # your WS API key
    base_url="http://baseurl",
)

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello, Claude!"}],
)
print(message.content[0].text)

📋 Request Body Parameters

Parameter	Type	Required	Description
model	string	Yes	Claude model ID, see Model Catalog
max_tokens	integer	Yes	Maximum number of tokens to generate
messages	array	Yes	Alternating user / assistant messages. Content is a string or an array of content blocks (text, image, tool_use, tool_result)
system	string / array	No	System prompt
stream	boolean	No	Stream the response via server-sent events
temperature	number	No	0–1. Default 1
top_p	number	No	Nucleus sampling
top_k	integer	No	Only sample from the top K options
stop_sequences	array	No	Custom stop sequences
tools	array	No	Tool definitions (name, description, input_schema)
tool_choice	object	No	{"type":"auto"} / {"type":"any"} / {"type":"tool","name":"..."}
thinking	object	No	Extended thinking, e.g. {"type":"enabled","budget_tokens":10000}
metadata	object	No	e.g. {"user_id": "..."}

📥 Response Fields

Field	Type	Description
id	string	Unique message identifier
type	string	Always message
role	string	Always assistant
model	string	Model used
content	array	Content blocks: text, tool_use, thinking
stop_reason	string	end_turn, max_tokens, stop_sequence, tool_use
usage	object	input_tokens, output_tokens, cache read/write token counts