Chat Completions

Generate conversational responses from AI models.

Endpoint: POST /api/v1/chat/completions
Auth: Required

Request Body

Field	Type	Required	Default	Description
messages	list[ChatMessage]	Yes	—	Conversation messages (min 1)
model	string	No	—	Model ID (e.g. openai/gpt-4o-mini)
provider	string	No	—	Provider name (inferred from model)
temperature	float	No	—	Sampling temperature
max_tokens	integer	No	—	Max tokens in response
top_p	float	No	—	Nucleus sampling
frequency_penalty	float	No	—	Frequency penalty
presence_penalty	float	No	—	Presence penalty
stream	boolean	No	false	Enable streaming
additional_params	object	No	{}	Provider-specific parameters
byok_api_key	string	No	—	Your own provider API key

ChatMessage

Field	Type	Description
role	string	system, user, or assistant
content	string or list	Text content or multimodal content array

Examples

PythonJavaScriptcURLOpenAI SDK

import requests

response = requests.post(
    "https://api.indoxhub.com/api/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "openai/gpt-4o-mini",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Explain quantum computing in simple terms."}
        ],
        "temperature": 0.7,
        "max_tokens": 500
    }
)
print(response.json()["data"])

const response = await fetch("https://api.indoxhub.com/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "openai/gpt-4o-mini",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "Explain quantum computing in simple terms." }
    ],
    temperature: 0.7,
    max_tokens: 500
  })
});
const data = await response.json();
console.log(data.data);

curl https://api.indoxhub.com/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 500
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.indoxhub.com/v1"
)
response = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    temperature=0.7,
    max_tokens=500
)
print(response.choices[0].message.content)

Response

{
  "request_id": "550e8400-e29b-41d4-a716-446655440000",
  "created_at": "2026-04-07T12:00:00Z",
  "duration_ms": 1200.5,
  "provider": "openai",
  "model": "gpt-4o-mini",
  "success": true,
  "message": "",
  "data": "Quantum computing uses quantum bits (qubits) that can exist in multiple states simultaneously...",
  "finish_reason": "stop",
  "reasoning_content": null,
  "images": null,
  "usage": {
    "tokens_prompt": 25,
    "tokens_completion": 150,
    "tokens_total": 175,
    "cost": 0.0052,
    "latency": 1200.5,
    "cache_read_tokens": 0,
    "cache_write_tokens": 0,
    "reasoning_tokens": 0,
    "web_search_count": 0
  }
}

Streaming

Set stream: true to receive Server-Sent Events (SSE):

import requests

response = requests.post(
    "https://api.indoxhub.com/api/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "openai/gpt-4o-mini",
        "messages": [{"role": "user", "content": "Tell me a story"}],
        "stream": True
    },
    stream=True
)

for line in response.iter_lines():
    if line:
        text = line.decode("utf-8")
        if text.startswith("data: ") and text != "data: [DONE]":
            print(text[6:], end="", flush=True)

See Streaming for full details.

Reasoning Content

Models that support reasoning (e.g., DeepSeek-R1) return a reasoning_content field:

{
  "data": "The answer is 42.",
  "reasoning_content": "Let me think step by step...",
  "finish_reason": "stop"
}