Anthropic Messages

POST /v1/messages

The Anthropic-native messaging format for Claude models. You can also call Claude models through the OpenAI-format Chat Completions endpoint.

RequestREQUEST

POSThttps://test.kailin.com.cn/v1/messages

API KeyStored only in your browser, never uploaded

Body (JSON)SSE stream · rendered live{ "model": "claude-sonnet-4-6", "max_tokens": 1024, "messages": [ { "role": "user", "content": "Hello, introduce yourself" } ], "stream": true }

ResponseRESPONSE

Fill in the request and hit Send — the response shows up here

Request

curl https://test.kailin.com.cn/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-your-token" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "Hello, introduce yourself" }
    ]
  }'

note

Both x-api-key: sk-xxx and Authorization: Bearer sk-xxx headers work. The anthropic-version header is optional.

Request Body

Parameter	Type	Required	Description
model	string	Yes	Claude model name
max_tokens	number	Yes	Max tokens to generate (required in the Anthropic format)
messages	array	Yes	Message array; role is only user / assistant
system	string / array	No	System prompt, passed separately from messages
stream	boolean	No	Stream output (SSE, event types below)
temperature	number	No	0–1, default 1
top_p / top_k	number	No	Sampling parameters
stop_sequences	array	No	Stop sequences
tools	array	No	Tool definitions (name / description / input_schema)
tool_choice	object	No	{"type": "auto"} / {"type": "any"} / {"type": "tool", "name": "..."}

Example with a system prompt and an image:

{
  "model": "claude-sonnet-4-6",
  "max_tokens": 1024,
  "system": "You are a rigorous technical writer.",
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "image", "source": { "type": "base64", "media_type": "image/jpeg", "data": "<base64>" } },
        { "type": "text", "text": "Describe this architecture diagram" }
      ]
    }
  ]
}

Response (Non-streaming)

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "model": "claude-sonnet-4-6",
  "content": [
    { "type": "text", "text": "Hello! I'm Claude…" }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 18,
    "output_tokens": 45
  }
}

Field	Description
content[]	Content blocks — type can be text / tool_use / thinking
stop_reason	end_turn / max_tokens / stop_sequence / tool_use
usage.input_tokens / output_tokens	Token usage

Streaming Events

With "stream": true the response is SSE with distinct event: types:

event: message_start
data: {"type":"message_start","message":{...}}

event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}

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

event: content_block_stop
data: {"type":"content_block_stop","index":0}

event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":45}}

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

Event	Description
message_start	Message starts, with initial usage
content_block_start / _delta / _stop	Content block start / delta / stop — deltas arrive in delta.text
message_delta	Top-level status update (stop_reason, final usage)
message_stop	Message ends
ping	Keep-alive heartbeat
error	In-stream error

Using the Anthropic SDK

from anthropic import Anthropic

client = Anthropic(
    api_key="sk-your-token",
    base_url="https://test.kailin.com.cn",
)

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

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  apiKey: 'sk-your-token',
  baseURL: 'https://test.kailin.com.cn',
});

const message = await client.messages.create({
  model: 'claude-sonnet-4-6',
  max_tokens: 1024,
  messages: [{ role: 'user', content: 'Hello' }],
});
console.log(message.content[0].text);

tip

For the SDK, set base_url to the root address (without /v1) — the SDK appends /v1/messages automatically.