Skip to main content
Novisurf is fully OpenAI-compatible. If you’re already using the OpenAI SDK, just swap the base URL and API key — nothing else changes.

​
Endpoint

POST https://api2.novisurf.top/v1/chat/completions

​
Authentication

Novisurf supports two ways to authenticate: X-API-Key header 
X-API-Key: lsk_...
Bearer token (Recommended) 
Authorization: Bearer lsk_...
Your API key is available in the Novisurf Dashboard.

​
Request

​
Headers

HeaderValue
Content-Typeapplication/json
Authorization BearerYour API key (lsk_...)

​
Body Parameters

ParameterTypeRequiredDescription
modelstringYesThe model to use. Check models in your console.
messagesarrayYesConversation history as an array of message objects.
streambooleanOptionalStream the response via SSE. Defaults to false.
temperaturenumberOptionalSampling temperature between 0 and 2. Defaults to 1.0.
max_tokensintegerOptionalMaximum tokens to generate.
top_pnumberOptionalNucleus sampling threshold between 0 and 1. Defaults to 1.0.
stopstring or arrayOptionalUp to 4 stop sequences.

​
Message Object

FieldTypeDescription
rolestringOne of system, user, or assistant.
contentstringThe message content.

​
Examples

​
Basic

curl https://api2.novisurf.top/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: lsk_..." \
  -d '{
    "model": "llama-3.3-70b-versatile",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "What is the capital of France?" }
    ]
  }'

​
Streaming

curl https://api2.novisurf.top/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: lsk_..." \
  -d '{
    "model": "llama-3.3-70b-versatile",
    "messages": [
      { "role": "user", "content": "Write me a short poem." }
    ],
    "stream": true
  }'

​
OpenAI SDK (drop-in)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "lsk_...",
  baseURL: "https://api2.novisurf.top/v1",
});

const response = await client.chat.completions.create({
  model: "llama-3.3-70b-versatile",
  messages: [
    { role: "user", content: "What is the capital of France?" }
  ],
});

console.log(response.choices[0].message.content);

​
Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="lsk_...",
    base_url="https://api2.novisurf.top/v1"
)

response = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[
        { "role": "user", "content": "What is the capital of France?" }
    ]
)

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

​
Response

​
Non-Streaming

{
  "id": "chatcmpl-a1b2c3d4e5f6",
  "object": "chat.completion",
  "created": 1745000000,
  "model": "llama-3.3-70b-versatile",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 9,
    "total_tokens": 33
  }
}

​
Streaming

Streamed responses are sent as SSE events and terminated with data: [DONE]. 
data: {"id":"chatcmpl-a1b2c3d4e5f6","object":"chat.completion.chunk","created":1745000000,"model":"llama-3.3-70b-versatile","choices":[{"index":0,"delta":{"role":"assistant","content":"The"},"finish_reason":null}]}

data: {"id":"chatcmpl-a1b2c3d4e5f6","object":"chat.completion.chunk","created":1745000000,"model":"llama-3.3-70b-versatile","choices":[{"index":0,"delta":{"content":" capital of France is Paris."},"finish_reason":"stop"}]}

data: [DONE]

​
Error Codes

StatusMeaning
400Bad request — missing or invalid parameters
401Unauthorized — invalid or missing API key
402Insufficient credits
429Rate limit exceeded
500Internal server error