API Call Examples - API 文档

Domains & Authentication

Note: The following examples need to replace the Authorization with the actual Login Code

Primary domain: https://ai.liaobots.work
Backup domains: https://ai.liaobots1.work, https://ai.liaobots2.work, https://ai.liaobots3.work
Keep the same path suffix when switching domains, such as /v1 or /v1beta

Check Balance

Query remaining credits for your auth code. The following two paths are equivalent — use either one: /api/v1/credits or /v1/credits.

Curl

curl 'https://ai.liaobots.work/api/v1/credits' \
  -H 'Authorization: Bearer <authcode>'

# Equivalent
curl 'https://ai.liaobots.work/v1/credits' \
  -H 'Authorization: Bearer <authcode>'

Response:

{
  "data": {
    "balance": 85.5,
    "amount": 100.0
  }
}

Field	Description
`balance`	Remaining available credits
`amount`	Total credits received

Check Credit Usage Records

Add include_usage=true to the balance endpoint to return detailed credit usage records. Use pageSize to control page size, and pass the returned nextId to fetch the next page.

Curl

curl 'https://ai.liaobots.work/api/v1/credits?include_usage=true&pageSize=50' \
  -H 'Authorization: Bearer <authcode>'

Response:

{
  "data": {
    "balance": 85.5,
    "amount": 100.0,
    "usage": {
      "pageSize": 50,
      "nextId": "1234567890",
      "list": [
        {
          "id": 1234567891,
          "tokens": 1200,
          "input_tokens": 800,
          "output_tokens": 400,
          "model": "gpt-5.4",
          "price": 0.12,
          "cache_hit_tokens": 0,
          "cache_creation_tokens": 0,
          "create_time": 1760000000000
        }
      ]
    }
  }
}

Field	Description
`usage.pageSize`	Page size returned by this request
`usage.nextId`	Cursor for the next page. Empty means there are no more records
`usage.list[].model`	Model or service used
`usage.list[].price`	Credits charged for this record
`usage.list[].tokens`	Total token count
`usage.list[].input_tokens`	Input token count
`usage.list[].output_tokens`	Output token count
`usage.list[].cache_hit_tokens`	Cache hit token count
`usage.list[].cache_creation_tokens`	Cache creation token count
`usage.list[].create_time`	Charge time as a Unix millisecond timestamp

OpenAI Format (Chat Completions)

Streaming Response

curl --location 'https://ai.liaobots.work/v1/chat/completions' \
--header 'Authorization: Bearer <authcode>' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gpt-5.4",
    "messages": [
        {
            "role": "user",
            "content": "Hi"
        }
    ],
    "temperature": 1,
    "stream": true
}'

from openai import OpenAI

client = OpenAI(
    api_key='authcode',
    base_url='https://ai.liaobots.work/v1'
)


stream = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {
            "role": "user",
            "content": "Hi"
        }
    ],
    stream=True,
)


for event in stream:
    if event.choices[0].delta.content:
        print(event.choices[0].delta.content)

Non-Streaming Response

curl --location 'https://ai.liaobots.work/v1/chat/completions' \
--header 'Authorization: Bearer <authcode>' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gpt-5.4",
    "messages": [
        {
            "role": "user",
            "content": "Hi"
        }
    ],
    "temperature": 1,
    "stream": false
}'

from openai import OpenAI

client = OpenAI(
    api_key='authcode',
    base_url='https://ai.liaobots.work/v1'
)


stream = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {
            "role": "user",
            "content": "Hi"
        }
    ],
    stream=False,
)


print(stream.choices[0].message.content)

Claude Format (Anthropic Messages)

Streaming Response

curl 'https://ai.liaobots.work/v1/messages' \
  -H 'x-api-key: <authcode>' \
  -H 'anthropic-version: 2023-06-01' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "stream": true,
    "messages": [
        {
            "role": "user",
            "content": "Hi"
        }
    ]
}'

import anthropic

client = anthropic.Anthropic(
    api_key='authcode',
    base_url='https://ai.liaobots.work'
)

with client.messages.stream(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Hi"
        }
    ],
) as stream:
    for text in stream.text_stream:
        print(text, end="")

Non-Streaming Response

curl 'https://ai.liaobots.work/v1/messages' \
  -H 'x-api-key: <authcode>' \
  -H 'anthropic-version: 2023-06-01' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [
        {
            "role": "user",
            "content": "Hi"
        }
    ]
}'

import anthropic

client = anthropic.Anthropic(
    api_key='authcode',
    base_url='https://ai.liaobots.work'
)

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

print(message.content[0].text)

OpenAI Responses API

Streaming Response

curl 'https://ai.liaobots.work/v1/responses' \
  -H 'Authorization: Bearer <authcode>' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-5.4",
    "stream": true,
    "input": "Hi"
}'

from openai import OpenAI

client = OpenAI(
    api_key='authcode',
    base_url='https://ai.liaobots.work/v1'
)

stream = client.responses.create(
    model="gpt-5.4",
    input="Hi",
    stream=True,
)

for event in stream:
    if hasattr(event, 'delta') and event.delta:
        print(event.delta, end="")

Non-Streaming Response

curl 'https://ai.liaobots.work/v1/responses' \
  -H 'Authorization: Bearer <authcode>' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-5.4",
    "input": "Hi"
}'

from openai import OpenAI

client = OpenAI(
    api_key='authcode',
    base_url='https://ai.liaobots.work/v1'
)

response = client.responses.create(
    model="gpt-5.4",
    input="Hi",
)

print(response.output_text)

Gemini Format (Gemini Native)

Non-Streaming Response

Curl

curl "https://ai.liaobots.work/v1beta/models/gemini-3-pro-preview(or other models):generateContent" \
  -H "x-goog-api-key: <authcode>" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "contents": [
      {
        "role": "system",
        "parts": [
          {
            "text": "You are a helpful assistant. Reply in Chinese."
          }
        ]
      },
      {
        "role": "user",
        "parts": [
          {
            "text": "Explain how AI works in a few words"
          }
        ]
      }
    ]
  }'

Streaming Response

Curl

curl "https://ai.liaobots.work/v1beta/models/gemini-3-pro-preview(or other models):streamGenerateContent?alt=sse" \
  -H "x-goog-api-key: <authcode>" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "contents": [
      {
        "role": "system",
        "parts": [
          {
            "text": "You are a helpful assistant. Reply in Chinese."
          }
        ]
      },
      {
        "role": "user",
        "parts": [
          {
            "text": "Explain how AI works in a few words"
          }
        ]
      }
    ]
  }'

Gemini Nano Banana 2/Pro

Non-Streaming Response

Curl

curl "https://ai.liaobots.work/v1beta/models/gemini-3-pro-image-preview:generateContent" \
  -H "x-goog-api-key: <authcode>" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
      "contents": [
          {
              "parts": [
                  {
                      "text": "Generate a visualization of the current weather in Tokyo."
                  }
              ]
          }
      ],
      "tools": [
          {
              "googleSearch": {}
          }
      ],
      "generationConfig": {
          "imageConfig": {
              "aspectRatio": "1:1",
              "imageSize": "2K"
          },
          "responseModalities":
          [
              "TEXT",
              "IMAGE"
          ]
      }
  }

Streaming Response

Curl

curl "https://ai.liaobots.work/v1beta/models/gemini-3-pro-image-preview:streamGenerateContent?alt=sse" \
  -H "x-goog-api-key: <authcode>" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
      "contents": [
          {
              "parts": [
                  {
                      "text": "Generate two dogs in manga style."
                  }
              ]
          }
      ],
      "generationConfig": {
          "imageConfig": {
              "aspectRatio": "16:9",
              "imageSize": "1K"
          },
          "responseModalities":
          [
              "TEXT",
              "IMAGE"
          ]
      }
  }

​Domains & Authentication

​Check Balance

​Check Credit Usage Records

​OpenAI Format (Chat Completions)

​Streaming Response

​Non-Streaming Response

​Claude Format (Anthropic Messages)

​Streaming Response

​Non-Streaming Response

​OpenAI Responses API

​Streaming Response

​Non-Streaming Response

​Gemini Format (Gemini Native)

​Non-Streaming Response

​Streaming Response

​Gemini Nano Banana 2/Pro

​Non-Streaming Response

​Streaming Response

Domains & Authentication

Check Balance

Check Credit Usage Records

OpenAI Format (Chat Completions)

Streaming Response

Non-Streaming Response

Claude Format (Anthropic Messages)

Streaming Response

Non-Streaming Response

OpenAI Responses API

Streaming Response

Non-Streaming Response

Gemini Format (Gemini Native)

Non-Streaming Response

Streaming Response

Gemini Nano Banana 2/Pro

Non-Streaming Response

Streaming Response