Anthropic API Compatible

Use this interface to call Ant Ling models, supporting multi-turn conversations, long-range tasks, and other scenarios. The payload format is fully compatible with Anthropic messages — you can integrate directly using the Anthropic SDK.

Request Address

Authorization

When calling the Anthropic-compatible API, either Authorization or x-api-key can be used to verify identity — exactly one is required.

Authorization

• Type: HTTP Bearer Auth, value type string
• Required (mutually exclusive with x-api-key)
• Description: Used to verify account information. Go to API Console , click Create Token to obtain.

Authorization: Bearer <YOUR_API_KEY>

x-api-key

• Type: string
• Required (mutually exclusive with Authorization)
• Description: Used to verify account information. Go to API Console  , click Create Token to obtain.

x-api-key: <YOUR_API_KEY>

Request Headers

Content-Type

• Type: enum<string>
• Required, fixed value application/json
• Description: The media type of the request body. Must be application/json.

Request Body

Overview

model

• Type: string
• Required
• Description: The ID of the model to call.
• Options: Ling-2.6-1T, Ling-2.6-flash, Ling-2.5-1T, Ling-1T, Ring-2.5-1T, Ring-1T

messages

• Type: object[]
• Required
• Description: The list of messages provided to the model, in conversation order. Supports text, tool_use, and tool_result content types.

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

messages.role

• Type: string
• Required
• Description: The role of the message sender.
• Options: user (user), assistant (assistant)

messages.content

• Type: string
• Required
• Description: The content of the message sent to the model.
• Example: Hello, Ant Ling

max_tokens

• Type: integer
• Optional, default 32000
• Description: Limits the maximum number of output tokens in a single model response.

stream

• Type: boolean
• Optional, default false
• Description: When set to true, enables streaming output. The server returns chunks in SSE format.

system

• Type: object[]
• Optional
• Description: System prompt used to set the model’s role or behavior.

[
  {
    "type": "text",
    "text": "You are an intelligent conversation assistant"
  }
]

tools

• Type: object[]
• Optional
• Description: Tool list (Function Calling). The model may invoke these tools in its reply.

[
  {
    "name": "search_city_weather",
    "description": "Search city weather",
    "input_schema": {
      "type": "object",
      "properties": {
        "city": {
          "type": "string",
          "description": "City name"
        },
        "date": {
          "type": "string",
          "description": "Date in yyyy-mm-dd format"
        }
      },
      "required": ["city", "date"]
    }
  }
]

tool_choice

• Type: object
• Optional, default { "type": "auto" }
• Description: Controls how the model uses tools.
• Types: auto (model decides), any (must use a tool), tool (use a specific tool), none (disable tools)

stop_sequences

• Type: string[]
• Optional
• Description: Stop sequences. The model stops generation early when it emits any string in this list.

temperature

• Type: double
• Optional, default 1
• Description: Controls randomness. Range [0.0, 1.0] — lower values are more deterministic, higher values more diverse.

top_p

• Type: double
• Optional, default 1
• Description: Nucleus sampling threshold. Range (0.0, 1.0] — lower values bias toward higher-probability tokens.

Request and Response

Request Example

curl --request POST \
  --url https://api.ant-ling.com/anthropic/v1/messages \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "Ling-2.6-flash",
  "stream": true,
  "messages": [
    {
      "role": "user",
      "content": "What opportunities and challenges will the Chinese large language model industry face in 2025?"
    }
  ]
}'

import anthropic
 
client = anthropic.Anthropic(
    base_url="https://api.ant-ling.com/anthropic",
    api_key="<YOUR_API_KEY>"
)
 
with client.messages.stream(
    model="Ling-2.6-flash",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "What opportunities and challenges will the Chinese large language model industry face in 2025?"}
    ]
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

import Anthropic from '@anthropic-ai/sdk';
 
const client = new Anthropic({
  baseURL: 'https://api.ant-ling.com/anthropic',
  apiKey: '<YOUR_API_KEY>',
});
 
const stream = client.messages.stream({
  model: 'Ling-2.6-flash',
  max_tokens: 1024,
  messages: [
    { role: 'user', content: 'What opportunities and challenges will the Chinese large language model industry face in 2025?' }
  ],
});
 
for await (const event of stream) {
  if (event.type === 'content_block_delta' && event.delta.type === 'text_delta') {
    process.stdout.write(event.delta.text);
  }
}

curl --request POST \
  --url https://api.ant-ling.com/anthropic/v1/messages \
  --header 'Authorization: Bearer <YOUR_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "Ling-2.6-flash",
  "messages": [
    {
      "role": "user",
      "content": "What opportunities and challenges will the Chinese large language model industry face in 2025?"
    }
  ]
}'

import anthropic
 
client = anthropic.Anthropic(
    base_url="https://api.ant-ling.com/anthropic",
    api_key="<YOUR_API_KEY>"
)
 
message = client.messages.create(
    model="Ling-2.6-flash",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "What opportunities and challenges will the Chinese large language model industry face in 2025?"}
    ]
)
 
print(message.content[0].text)

import Anthropic from '@anthropic-ai/sdk';
 
const client = new Anthropic({
  baseURL: 'https://api.ant-ling.com/anthropic',
  apiKey: '<YOUR_API_KEY>',
});
 
const message = await client.messages.create({
  model: 'Ling-2.6-flash',
  max_tokens: 1024,
  messages: [
    { role: 'user', content: 'What opportunities and challenges will the Chinese large language model industry face in 2025?' }
  ],
});
 
console.log(message.content[0].text);

Response Example

event: message_start
data: {"message":{"content":[],"id":"0be8c630...","model":"Ling-2.6-flash","role":"assistant","type":"message","usage":{"input_tokens":0,"output_tokens":0}},"type":"message_start"}

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

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

event: content_block_delta
data: {"delta":{"text":"! How can I help you today?","type":"text_delta"},"index":0,"type":"content_block_delta"}

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

event: message_delta
data: {"delta":{"stop_reason":"end_turn"},"type":"message_delta","usage":{"input_tokens":19,"output_tokens":21}}

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

{
  "content": [
    {
      "text": "Hello! How can I help you today?",
      "type": "text"
    }
  ],
  "id": "0be8ed25...",
  "model": "Ling-2.6-flash",
  "role": "assistant",
  "stop_reason": "end_turn",
  "type": "message",
  "usage": {
    "input_tokens": 19,
    "output_tokens": 24
  }
}