Chat Completions

1. Endpoint

/v1/chat/completions

2. Method

POST

3. Request Parameters

Header

Body

Model List

Object Schemas

Message

4. Response Parameters

Non-streaming requests return a chat.completion object.

choices

message

usage

Streaming requests return text/event-stream. Each event starts with data: and the stream ends with data: [DONE].

5. Examples

Non-streaming request

curl -X POST https://hiharness.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -d '{
    "model": "qwen3.5-plus",
    "messages": [
      {"role": "system", "content": "You are a helpful AI assistant."},
      {"role": "user", "content": "Hello, please introduce yourself."}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

Non-streaming response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1748236800,
  "model": "qwen3.5-plus",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I am an AI assistant. How can I help you?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 18,
    "total_tokens": 33
  }
}

Streaming request

curl -X POST https://hiharness.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -d '{
    "model": "qwen3.5-plus",
    "messages": [
      {"role": "system", "content": "You are a helpful AI assistant."},
      {"role": "user", "content": "Hello, please introduce yourself."}
    ],
    "stream": true,
    "temperature": 0.7,
    "max_tokens": 1024
  }'

Streaming response

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1748236800,"model":"qwen3.5-plus","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1748236800,"model":"qwen3.5-plus","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1748236800,"model":"qwen3.5-plus","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1748236800,"model":"qwen3.5-plus","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

6. Python Examples

requests non-streaming

import requests

BASE_URL = "https://hiharness.ai"
API_KEY = "sk-xxxxxxxx"

headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}",
}

payload = {
    "model": "qwen3.5-plus",
    "messages": [
        {"role": "system", "content": "You are a helpful AI assistant."},
        {"role": "user", "content": "Hello, please introduce yourself."},
    ],
    "temperature": 0.7,
    "max_tokens": 1024,
}

response = requests.post(
    f"{BASE_URL}/v1/chat/completions",
    headers=headers,
    json=payload,
)
response.raise_for_status()

result = response.json()
print(result["choices"][0]["message"]["content"])

requests streaming

import json
import requests

BASE_URL = "https://hiharness.ai"
API_KEY = "sk-xxxxxxxx"

headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}",
}

payload = {
    "model": "qwen3.5-plus",
    "messages": [
        {"role": "system", "content": "You are a helpful AI assistant."},
        {"role": "user", "content": "Hello, please introduce yourself."},
    ],
    "stream": True,
    "temperature": 0.7,
    "max_tokens": 1024,
}

response = requests.post(
    f"{BASE_URL}/v1/chat/completions",
    headers=headers,
    json=payload,
    stream=True,
)
response.raise_for_status()

for line in response.iter_lines():
    if not line:
        continue
    line = line.decode("utf-8")
    if not line.startswith("data: "):
        continue
    data = line[6:]
    if data == "[DONE]":
        break
    chunk = json.loads(data)
    delta = chunk["choices"][0]["delta"]
    if "content" in delta:
        print(delta["content"], end="", flush=True)

print()

OpenAI Python Client non-streaming

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxx",
    base_url="https://hiharness.ai/v1",
)

response = client.chat.completions.create(
    model="qwen3.5-plus",
    messages=[
        {"role": "system", "content": "You are a helpful AI assistant."},
        {"role": "user", "content": "Hello, please introduce yourself."},
    ],
    temperature=0.7,
    max_tokens=1024,
)

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

OpenAI Python Client streaming

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxx",
    base_url="https://hiharness.ai/v1",
)

stream = client.chat.completions.create(
    model="qwen3.5-plus",
    messages=[
        {"role": "system", "content": "You are a helpful AI assistant."},
        {"role": "user", "content": "Hello, please introduce yourself."},
    ],
    stream=True,
    temperature=0.7,
    max_tokens=1024,
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="", flush=True)

print()

7. Error Codes