First Request

After setting up authentication, you're ready to make your first API request. This guide walks you through each part of a request and explains the response.

Basic Request

The most common endpoint is Chat Completions, which generates a response based on a list of messages:

curl https://openapi.linkwo.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-pro",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "temperature": 0.7
  }'

Understanding the Response

A successful response returns JSON like this:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1719000000,
  "model": "deepseek/deepseek-v4-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 8,
    "total_tokens": 32
  }
}

Key Fields

Field	Description
`id`	Unique identifier for the completion
`choices`	Array of completion choices (usually one)
`choices[].message`	The assistant's reply
`choices[].finish_reason`	Why the model stopped generating (`stop`, `length`, `content_filter`)
`usage`	Token counts for billing and monitoring

Message Roles

Each message has a role that tells the model how to interpret it:

Role	Description
`system`	Sets the assistant's behavior and personality
`user`	The end-user's input or instruction
`assistant`	The model's previous replies (for multi-turn conversations)

Multi-Turn Conversation

Include previous messages to maintain context:

from openai import OpenAI

client = OpenAI(
    base_url="https://openapi.linkwo.ai/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-pro",
    messages=[
        {"role": "system", "content": "You are a travel guide."},
        {"role": "user", "content": "What's the best time to visit Japan?"},
        {"role": "assistant", "content": "The best time to visit Japan is during spring (March-May) for cherry blossoms or autumn (October-November) for fall foliage."},
        {"role": "user", "content": "What about budget-friendly options?"}
    ]
)

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

Common Parameters

Parameter	Type	Default	Description
`temperature`	float	1.0	Controls randomness (0 = deterministic, 2 = very random)
`max_tokens`	int	model max	Maximum tokens to generate in the response
`top_p`	float	1.0	Nucleus sampling threshold
`stream`	bool	false	Stream partial results as they're generated

Error Handling

If something goes wrong, the API returns an error object:

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}

Common HTTP status codes:

Status	Meaning
400	Bad request — check your parameters
401	Unauthorized — invalid or missing API key
429	Rate limit exceeded — slow down or upgrade
500	Server error — retry after a brief wait

See Error Codes for the complete list.

Next Steps

Streaming Response — Get real-time streaming output
Chat Completions API — Full API reference
SDK Integration — Use SDKs in your language

Authentication

Streaming Response