Claude Messages

Call Claude models via the Anthropic Messages API native protocol. Fully compatible with Claude SDK, Claude Code, and the native Anthropic request format.

Try it now

Test in Playground ↗ · View Model List ↗

Quick Start

Step 1: Get your API Key from the Console.

Step 2: Send a request:

cURLPythonNode.js

bash

curl -X POST "https://open.dieyuyun.com/v1/messages" \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-xxx" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello, introduce yourself"}
    ]
  }'

python

import anthropic

client = anthropic.Anthropic(
    base_url="https://open.dieyuyun.com",
    api_key="sk-xxx"
)

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello, introduce yourself"}
    ]
)

print(message.content[0].text)

javascript

import Anthropic from '@anthropic-ai/sdk'

const client = new Anthropic({
  baseURL: 'https://open.dieyuyun.com',
  apiKey: 'sk-xxx',
})

const message = await client.messages.create({
  model: 'claude-sonnet-4-20250514',
  max_tokens: 1024,
  messages: [{ role: 'user', content: 'Hello, introduce yourself' }],
})

console.log(message.content[0].text)

Step 3: Read the response from content[0].text.

Endpoint

Item	Value
Method	POST
Path	`/v1/messages`
Base URL	`https://open.dieyuyun.com`
Protocol	Anthropic Messages API

Authentication

The Claude Messages API uses the following authentication headers:

Header	Value	Description
x-api-key	`sk-xxx`	API Key authentication
anthropic-version	`2023-06-01`	Anthropic API version
Content-Type	`application/json`	Request body format

TIP

When using the Anthropic SDK, the anthropic-version header is added automatically. You only need to configure base_url and api_key.

Supported Models

Model	Context Length	Description
claude-sonnet-4-20250514	200K	Claude 4 Sonnet, balanced
claude-opus-4-20250514	200K	Claude 4 Opus, strongest
claude-3-5-sonnet-20241022	200K	Claude 3.5 Sonnet
claude-3-5-haiku-20241022	200K	Claude 3.5 Haiku, fast
claude-3-opus-20240229	200K	Claude 3 Opus

TIP

See the full model list in the Console.

Request Parameters

Field	Type	Required	Default	Description
model	string	Yes	—	Model identifier, e.g. `claude-sonnet-4-20250514`
messages	array	Yes	—	Message list, supports `user` and `assistant` roles
max_tokens	integer	Yes	—	Maximum output tokens (required in Anthropic protocol)
system	string / array	No	—	System prompt, separate from messages
stream	boolean	No	false	Enable streaming output
temperature	number	No	1.0	Sampling randomness, range 0~1
top_p	number	No	—	Nucleus sampling parameter
top_k	integer	No	—	Top-K sampling
stop_sequences	array	No	—	Strings that stop generation
tools	array	No	—	Tool definitions (function calling)
tool_choice	object	No	—	Tool calling strategy
thinking	object	No	—	Extended Thinking configuration
metadata	object	No	—	Request metadata, e.g. `user_id`

Message Format

The message structure in Claude Messages API differs from OpenAI:

json

{
  "role": "user",
  "content": "Hello"
}

Multimodal content is also supported:

json

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

Request Examples

Conversation with System Prompt

cURLPythonNode.js

bash

curl -X POST "https://open.dieyuyun.com/v1/messages" \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-xxx" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "system": "You are a professional Python developer. Keep answers concise.",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "What are Python decorators? Give an example."}
    ]
  }'

python

import anthropic

client = anthropic.Anthropic(
    base_url="https://open.dieyuyun.com",
    api_key="sk-xxx"
)

message = client.messages.create(
    model="claude-sonnet-4-20250514",
    system="You are a professional Python developer. Keep answers concise.",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "What are Python decorators? Give an example."}
    ]
)

print(message.content[0].text)

javascript

import Anthropic from '@anthropic-ai/sdk'

const client = new Anthropic({
  baseURL: 'https://open.dieyuyun.com',
  apiKey: 'sk-xxx',
})

const message = await client.messages.create({
  model: 'claude-sonnet-4-20250514',
  system: 'You are a professional Python developer. Keep answers concise.',
  max_tokens: 1024,
  messages: [{ role: 'user', content: 'What are Python decorators? Give an example.' }],
})

console.log(message.content[0].text)

Streaming Output

python

import anthropic

client = anthropic.Anthropic(
    base_url="https://open.dieyuyun.com",
    api_key="sk-xxx"
)

with client.messages.stream(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Write a quicksort algorithm"}
    ]
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

Tool Calling (Function Calling)

json

{
  "model": "claude-sonnet-4-20250514",
  "max_tokens": 1024,
  "messages": [{ "role": "user", "content": "What's the weather like in Beijing today?" }],
  "tools": [
    {
      "name": "get_weather",
      "description": "Get weather information for a city",
      "input_schema": {
        "type": "object",
        "properties": {
          "city": {
            "type": "string",
            "description": "City name"
          }
        },
        "required": ["city"]
      }
    }
  ]
}

Response Format

Successful Response

json

{
  "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! I'm Claude, an AI assistant developed by Anthropic. I'm happy to help you."
    }
  ],
  "model": "claude-sonnet-4-20250514",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 12,
    "output_tokens": 32
  }
}

Field Reference

Field	Description
id	Unique message identifier
type	Always `message`
role	Always `assistant`
content	Array of response blocks, may include `text` and `tool_use` types
model	Actual model ID used
stop_reason	Stop reason: `end_turn`, `max_tokens`, `tool_use`, `stop_sequence`
usage.input_tokens	Number of input tokens
usage.output_tokens	Number of output tokens

Streaming SSE Events

Streaming output returns the native Claude SSE event stream:

event: message_start
data: {"type":"message_start","message":{"id":"msg_01...","type":"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_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"! I'm"}}

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":32}}

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

Error Response

json

{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens: field required"
  }
}

See Error Codes for details.

Compatibility

Feature	Wuliang AI	Anthropic Native API
Messages protocol	Fully compatible	Native protocol
System prompt	Separate `system` parameter	Separate `system` parameter
Multimodal (images)	Supports base64	Supports base64 / URL
Tool calling	Pass-through support	Native support
Streaming SSE	Native Claude event stream	Native protocol
Extended Thinking	Pass-through support	Native support
Authentication	x-api-key	x-api-key
anthropic-version	Required	Required

TIP

The platform maintains full compatibility with the Anthropic Messages API. Successful responses return the native Claude format directly, without additional code / data wrappers. You can integrate using the Anthropic SDK by simply changing the base_url.

Best Practices

Always set max_tokens: Unlike the OpenAI protocol, the Anthropic Messages API requires the max_tokens parameter.
Use the system parameter: Claude's system prompt is a separate parameter -- do not place it in messages.
Claude Code support: This platform supports direct Claude Code connections. Simply configure the base_url.
Token counting differences: Anthropic's tokenization may differ from OpenAI's, so the same text may produce different token counts.
Tool calling syntax: Claude tools use input_schema (not OpenAI's parameters). Be aware of the field name difference.

Rate Limits

See Rate Limits for details.

Chat Completions (Streaming) - Use the OpenAI-compatible protocol
Gemini Native Format - Use the Gemini native protocol
OpenAI Responses - Use the OpenAI Responses API
Manage API Keys - Create and configure API keys

Claude Messages ​

Quick Start ​

Endpoint ​

Authentication ​

Supported Models ​

Request Parameters ​

Message Format ​

Request Examples ​

Conversation with System Prompt ​

Streaming Output ​

Tool Calling (Function Calling) ​

Response Format ​

Successful Response ​

Field Reference ​

Streaming SSE Events ​

Error Response ​

Compatibility ​

Best Practices ​

Rate Limits ​

Related Docs ​

Claude Messages

Quick Start

Endpoint

Authentication

Supported Models

Request Parameters

Message Format

Request Examples

Conversation with System Prompt

Streaming Output

Tool Calling (Function Calling)

Response Format

Successful Response

Field Reference

Streaming SSE Events

Error Response

Compatibility

Best Practices

Rate Limits

Related Docs