Examples

Practical code examples for common integration patterns.

Chat Completion

Send a message and receive a complete model response.

Request Example

cURL

curl https://gateway.hkting.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 500
  }'

Response Example

json

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1734567890,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing uses qubits instead of bits..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 142,
    "total_tokens": 160
  }
}

Streaming

Receive responses incrementally via Server-Sent Events (SSE) for real-time applications.

Request Example

cURL

curl https://gateway.hkting.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Write a short poem about AI."}
    ],
    "stream": true
  }'

Tool Calling (Function Calling)

Let the model call functions defined in your request to fetch data or take actions.

Request Example

cURL

curl https://gateway.hkting.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "What'''s the weather like in Paris today?"}
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get the current weather for a city",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "City name"
              }
            },
            "required": ["location"]
          }
        }
      }
    ],
    "tool_choice": "auto"
  }'

Response Example

json

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": [
          {
            "id": "call_abc123",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"location\":\"Paris\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls"
    }
  ]
}

The model decides when to call a tool. If it does, the response includes a tool_calls field instead of content. You then send the tool result back to continue the conversation.

Embeddings

Generate vector embeddings for text input using supported embedding models.

Request Example

cURL

curl https://gateway.hkting.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -d '{
    "model": "text-embedding-ada-002",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Agent Integration

Configure AI coding agents and assistants to use HuiLink as their API backend.

Configuration

bash

# Configure Claude Code to use Token Gateway
export ANTHROPIC_BASE_URL=https://gateway.hkting.com
export ANTHROPIC_API_KEY=sk-your-api-key

# Start a Claude Code session
claude

Claude Code uses Anthropic's Messages API format. HuiLink provides protocol conversion between OpenAI and Anthropic formats, enabling seamless integration with both ecosystems.

curl https://gateway.hkting.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-your-api-key" \ -d '{ "model": "gpt-4o", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Explain quantum computing in simple terms."} ], "temperature": 0.7, "max_tokens": 500 }'

{ "id": "chatcmpl-xxx", "object": "chat.completion", "created": 1734567890, "model": "gpt-4o", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Quantum computing uses qubits instead of bits..." }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 18, "completion_tokens": 142, "total_tokens": 160 } }

curl https://gateway.hkting.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-your-api-key" \ -d '{ "model": "gpt-4o", "messages": [ {"role": "user", "content": "Write a short poem about AI."} ], "stream": true }'

curl https://gateway.hkting.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-your-api-key" \ -d '{ "model": "gpt-4o", "messages": [ {"role": "user", "content": "What'''s the weather like in Paris today?"} ], "tools": [ { "type": "function", "function": { "name": "get_weather", "description": "Get the current weather for a city", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "City name" } }, "required": ["location"] } } } ], "tool_choice": "auto" }'

{ "id": "chatcmpl-xxx", "object": "chat.completion", "choices": [ { "index": 0, "message": { "role": "assistant", "content": null, "tool_calls": [ { "id": "call_abc123", "type": "function", "function": { "name": "get_weather", "arguments": "{\"location\":\"Paris\"}" } } ] }, "finish_reason": "tool_calls" } ] }

curl https://gateway.hkting.com/v1/embeddings \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-your-api-key" \ -d '{ "model": "text-embedding-ada-002", "input": "The quick brown fox jumps over the lazy dog" }'