Chat Completions

OpenAI-compatible chat completions endpoint

POST /v1/chat/completions

Chat Completions

cURL

curl --request POST \
  --url https://api.ajstudioz.co.in/v1/chat/completions \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "stream": true,
  "temperature": 123,
  "max_tokens": 123,
  "top_p": 123,
  "stop": {},
  "tools": [
    {}
  ],
  "tool_choice": {},
  "response_format": {}
}
'

Response

{
  "id": "chatcmpl-abc123xyz",
  "object": "chat.completion",
  "created": 1751760000,
  "model": "gemma3:27b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 9,
    "total_tokens": 23
  }
}

Overview

Create a chat completion using the OpenAI-compatible API format. Works with any OpenAI SDK, LangChain, LlamaIndex, and tools like Cursor or Continue.

Request

Headers

Authorization · string · required

Bearer token: Bearer YOUR_API_KEY

Body

model · string · required

Model identifier. See available models. Example: "gemma3:27b", "deepseek-v3.2".

messages · array · required

Array of message objects:

• role — "system", "user", or "assistant"
• content — message text (or array of content objects for vision)

stream · boolean · default: "false"

If true, returns a stream of text/event-stream Server-Sent Events.

temperature · number · default: "1"

Sampling temperature between 0 and 2. Higher = more random, lower = more focused.

max_tokens · integer

Maximum number of tokens to generate. If unset, uses model default.

top_p · number · default: "1"

Nucleus sampling probability mass. Use with temperature not both.

stop · string or array

Up to 4 sequences where the model will stop generating tokens.

tools · array

List of tool definitions for function calling. Each tool has type: "function" and a function object with name, description, and parameters (JSON Schema).

tool_choice · string or object · default: "auto"

Controls how the model responds to tools. Values: "none", "auto", or {"type": "function", "function": {"name": "..."}}

response_format · object

Set to {"type": "json_object"} to enable JSON mode.

---

Response

id · string

Unique identifier for this completion.

object · string

"chat.completion" or "chat.completion.chunk" for streaming.

created · integer

Unix timestamp when the completion was created.

model · string

The model used.

choices · array

Array of completion choices. Usually one unless n > 1:

• index — choice index
• message.role — "assistant"
• message.content — generated text
• finish_reason — "stop", "length", or "tool_calls"

usage · object

Token usage statistics:

• prompt_tokens
• completion_tokens
• total_tokens

---

Examples

OpenAI SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ajstudioz.co.in/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="gemma3:27b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing briefly."}
    ],
    temperature=0.7,
    max_tokens=512
)

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

Response

{
  "id": "chatcmpl-abc123xyz",
  "object": "chat.completion",
  "created": 1751760000,
  "model": "gemma3:27b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 9,
    "total_tokens": 23
  }
}