API

Basics

Authentication

Every request must include your API key in the Authorization header:

Authorization: Bearer unit23-sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

• Key format: unit23-sk- followed by 48 hexadecimal characters.
• Missing or invalid keys return 401.

Chat completions

POST /v1/chat/completions creates a chat completion. Both streaming and non-streaming responses are supported.

Request parameters

cURL

curl https://api.unit23api.com/v1/chat/completions \
  -H "Authorization: Bearer unit23-sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "max_tokens": 100,
    "temperature": 0.7
  }'

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.unit23api.com/v1",
    api_key="unit23-sk-xxx",
)

response = client.chat.completions.create(
    model="deepseek-v3",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
    max_tokens=100,
    temperature=0.7,
)

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

JavaScript / TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.unit23api.com/v1",
  apiKey: "unit23-sk-xxx",
});

const response = await client.chat.completions.create({
  model: "deepseek-v3",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello!" },
  ],
  max_tokens: 100,
  temperature: 0.7,
});

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

Non-streaming response

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1713456789,
  "model": "default",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 21,
    "completion_tokens": 9,
    "total_tokens": 30
  }
}

Some models return default in the model field. This does not affect actual usage.

Streaming

Set stream: true to receive Server-Sent Events.

curl https://api.unit23api.com/v1/chat/completions \
  -H "Authorization: Bearer unit23-sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

SSE response

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"delta":{"role":"assistant"},"index":0}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":"Hello"},"index":0}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":"!"},"index":0}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[],"usage":{"prompt_tokens":10,"completion_tokens":5,"total_tokens":15}}

data: [DONE]

• The last non-empty data line carries the usage field — we automatically inject stream_options.include_usage=true.
• With the standard OpenAI SDK, the streaming call looks identical to the official API.

Available models

Unsupported names

The following return 404 Not Found:

• Provider-prefixed forms (e.g. deepseek/xxx, minimax/xxx).
• Official upstream aliases such as deepseek-chat, deepseek-reasoner.
• Any model name not listed above.

Parameter support

Errors

Error response

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

Limits & notes

1. Request timeout: 30 seconds — returns 504 on timeout.
2. Model name case: MiniMax-M2.5 is case-insensitive; minimax-m2.5 works too.
3. Streaming usage: the last SSE chunk contains usage; non-streaming responses include it at the root level.
4. CORS: enabled — callable directly from browsers.
5. Content safety: please comply with applicable laws. Generating illegal or harmful content is prohibited.

Support

Questions or trouble? Email hello@unit23.xyz.