API Reference

Overview

• Base URL: https://open.dieyuyun.com
• Authentication: Bearer Token or x-api-key header (get your API Key from the console)
• Protocol: HTTPS

Chat Completions

Text generation endpoint with multi-turn conversation and streaming support.

Request

POST /v1/chat/completions

Parameters

Parameter	Type	Required	Description
model	string	Yes	Model code, e.g. deepseek-v4-flash
messages	array	Yes	Message list
messages.role	string	Yes	Role: system, user, assistant
messages.content	string	Yes	Message content
temperature	number	No	Temperature, 0-2, default 1
max_tokens	integer	No	Max tokens to generate
top_p	number	No	Top-p sampling, 0-1, default 1
stream	boolean	No	Enable streaming, default false

Request Example

{
  "model": "deepseek-v4-flash",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Hello!" }
  ],
  "temperature": 0.7,
  "max_tokens": 1024
}

Response

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 10,
    "total_tokens": 30
  }
}

Streaming

Set stream: true to receive Server-Sent Events:

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":"!"},"finish_reason":null}]}

data: [DONE]

The last chunk in a streaming response includes a usage field for token statistics.

Messages (Anthropic Compatible)

Anthropic Messages API compatible endpoint for text generation. Use the Anthropic SDK to call directly.

Request

POST /v1/messages

Authentication

Two methods are supported:

• x-api-key: <your-api-key> (recommended, default for Anthropic SDK)
• Authorization: Bearer <your-api-key>

Parameters

Parameter	Type	Required	Description
model	string	Yes	Model code, e.g. deepseek-v4-flash
messages	array	Yes	Message list
messages.role	string	Yes	Role: user, assistant
messages.content	string/array	Yes	Message content, supports string or content blocks
system	string/array	No	System prompt, supports string or content blocks
max_tokens	integer	Yes	Max tokens to generate
temperature	number	No	Temperature, 0-1, default 1
top_p	number	No	Top-p sampling, 0-1, default 1
stream	boolean	No	Enable streaming, default false
stop_sequences	array	No	List of stop sequences

Request Example

{
  "model": "deepseek-v4-flash",
  "max_tokens": 1024,
  "system": "You are a helpful assistant.",
  "messages": [{ "role": "user", "content": "Hello!" }]
}

Using the Anthropic Python SDK:

import anthropic

client = anthropic.Anthropic(
    base_url="https://open.dieyuyun.com",
    api_key="your-api-key"
)

message = client.messages.create(
    model="deepseek-v4-flash",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(message.content[0].text)

Response

{
  "id": "msg_xxx",
  "type": "message",
  "role": "assistant",
  "model": "deepseek-v4-flash",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you today?"
    }
  ],
  "usage": {
    "input_tokens": 10,
    "output_tokens": 10
  }
}

Streaming

Set stream: true to receive Server-Sent Events. The event sequence is:

event: message_start
data: {"type":"message_start","message":{"id":"msg_xxx","type":"message","role":"assistant","model":"deepseek-v4-flash","stop_reason":null,"usage":{"input_tokens":10,"output_tokens":0}}}

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":"!"}}

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":10}}

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

finish_reason Mapping

Anthropic stop_reason	OpenAI finish_reason	Description
end_turn	stop	Normal stop
max_tokens	length	Max tokens hit

Search Completions

Web search endpoint that generates answers based on real-time search results.

Request

POST /v1/search/completions

Parameters

Parameter	Type	Required	Description
model	string	Yes	Model code that supports search
messages	array	Yes	Message list, same as Chat Completions
stream	boolean	No	Enable streaming, default false

Request Example

{
  "model": "deepseek-v4-flash",
  "messages": [{ "role": "user", "content": "What are today's tech news?" }]
}

Response

The response format is the same as Chat Completions, with search source citations included in the answer.

Images Generations

Generate images from text descriptions.

Request

POST /v1/images/generations

Parameters

Parameter	Type	Required	Description
model	string	Yes	Image generation model code
prompt	string	Yes	Text description of the image
n	integer	No	Number of images to generate, default 1
size	string	No	Image size, e.g. 1024x1024
response_format	string	No	Response format: url (default) or b64_json

Request Example

{
  "model": "gpt-image-2",
  "prompt": "A white cat sitting on a windowsill",
  "n": 1,
  "size": "1024x1024"
}

Response

{
  "created": 1700000000,
  "data": [
    {
      "url": "https://cdn.wuliang.ai/images/xxx.png"
    }
  ]
}

Balance

Queries the available balance of the tenant that owns the current API Key, along with that Key's daily/monthly budget usage. Useful for "usage query" features in third-party tools like CC Switch.

Request

GET /v1/balance HTTP/1.1
Host: open.dieyuyun.com
Authorization: Bearer sk-xxxxxxxxxxxxxxxx

No query parameters, no request body.

Response

{
  "object": "balance",
  "currency": "CNY",
  "balance": 138.5,
  "api_key": {
    "id": "1923456789012345678",
    "name": "claude-code",
    "daily_budget": 20.0,
    "daily_used": 3.25,
    "daily_remaining": 16.75,
    "daily_reset_at": "2026-06-09T00:00:00+08:00",
    "monthly_budget": null,
    "monthly_used": null,
    "monthly_remaining": null,
    "monthly_reset_at": null
  }
}

Field	Description
currency	Fixed CNY.
balance	Total available (yuan) = top-up balance + gift balance.
api_key.id / api_key.name	ID and name of the current API Key.
api_key.daily_budget	Per-Key daily budget (yuan), null if not set.
api_key.daily_used / daily_remaining	Consumed / remaining today (yuan).
api_key.daily_reset_at	Next daily budget reset time (ISO8601).
api_key.monthly_*	Monthly equivalents of the fields above.

See Connect CC Switch for full third-party tool configuration examples.

Error Codes

HTTP Status	Code	Description
400	INVALID_PARAMS	Invalid request parameters
401	UNAUTHORIZED	Invalid or expired API Key
403	FORBIDDEN	Access denied
404	MODEL_NOT_FOUND	Model not found or offline
429	RATE_LIMIT	Rate limit exceeded
500	INTERNAL_ERROR	Internal server error
502	UPSTREAM_ERROR	Upstream model service error
504	GATEWAY_TIMEOUT	Request timeout

All error responses use JSON format:

{
  "error": {
    "code": "RATE_LIMIT",
    "message": "Rate limit exceeded. Please retry after 60s.",
    "request_id": "req-xxx"
  }
}

Use request_id to trace issues in the console request logs.

Rate Limits

• Default RPM (Requests Per Minute): 60
• Default TPM (Tokens Per Minute): 100,000
• Configurable per API Key in the console

When rate limited, a 429 status is returned with these response headers:

• X-RateLimit-Limit: Total limit for the current window
• X-RateLimit-Remaining: Remaining requests in the current window
• Retry-After: Suggested retry wait time in seconds