Core Concepts

Chat & Messages API

The Chat API is the primary interface for conversations, reasoning, and code generation with Cortiqa models like openai/gpt-oss-120b. It supports multi-turn dialogues, system instructions, real-time streaming, and tool calls.

Basic Request

chat.py

1import cortiqa
2
3client = cortiqa.Client()
4
5response = client.chat.create(
6    model="openai/gpt-oss-120b",
7    messages=[
8        {"role": "user", "content": "What is machine learning?"}
9    ],
10    temperature=0.7
11)
12
13print(response.content)

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID, e.g. `openai/gpt-oss-120b` or `cortiqa/falin-1`
`messages`	array	Yes	Array of role/content objects (system, user, assistant)
`max_tokens`	integer	No	Maximum tokens to generate (up to 131K context)
`temperature`	float	No	Sampling temperature (0.0 to 2.0). Default: 0.7
`top_p`	float	No	Nucleus sampling probability threshold
`stream`	boolean	No	Enable SSE token streaming. Default: false
`tools`	array	No	List of tool definitions for function calling
`stop`	array	No	Custom stop sequences

Response Format

Response JSON

{
  "id": "chatcmpl-01JHE7N9",
  "object": "chat.completion",
  "created": 1726982400,
  "model": "openai/gpt-oss-120b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Machine learning is a subset of artificial intelligence where algorithms learn patterns from data..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 84,
    "total_tokens": 96
  }
}

Multi-turn Conversations

Include the historical conversation turns to maintain context:

multi_turn.py

1response = client.chat.create(
2    model="openai/gpt-oss-120b",
3    messages=[
4        {"role": "user", "content": "What is Python?"},
5        {"role": "assistant", "content": "Python is a high-level, readable programming language..."},
6        {"role": "user", "content": "What are its 3 biggest advantages for AI development?"}
7    ]
8)
9print(response.content)

System Prompts

Provide a system message at index 0 to steer model persona and formatting rules:

system_prompt.py

response = client.chat.create(
    model="openai/gpt-oss-120b",
    messages=[
        {"role": "system", "content": "You are a senior systems engineer at Cortiqa. Respond strictly in valid JSON."},
        {"role": "user", "content": "List 3 Linux diagnostic commands."}
    ]
)

System Prompt Best Practices

System prompts help ensure consistent tone, JSON output formatting, and domain constraints. Explore our System Prompts guide for advanced patterns.

Was this page helpful?

Models

Streaming