Skip to content
Kindo Kindo Docs

Chat Completions API quickstart

POST https://api.kindo.ai/v1/chat/completions speaks the OpenAI Chat Completions API. Stock OpenAI clients work unmodified.

Prerequisites

openai-python

import os
from openai import OpenAI


client = OpenAI(
    base_url="https://api.kindo.ai/v1",
    api_key=os.environ["KINDO_API_KEY"],
)


response = client.chat.completions.create(
    model="claude-sonnet-4-5-20250929",
    messages=[
        {"role": "user", "content": "Explain Kubernetes pod security policies."}
    ],
)


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

openai-node

import OpenAI from 'openai';


const client = new OpenAI({
  baseURL: 'https://api.kindo.ai/v1',
  apiKey: process.env.KINDO_API_KEY
});


const response = await client.chat.completions.create({
  model: 'claude-sonnet-4-5-20250929',
  messages: [
    { role: 'user', content: 'Explain Kubernetes pod security policies.' }
  ]
});


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

curl

Terminal window
curl -X POST https://api.kindo.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $KINDO_API_KEY" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "messages": [
      { "role": "user", "content": "Explain Kubernetes pod security policies." }
    ]
  }'

Response shape

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1710000000,
  "model": "claude-sonnet-4-5-20250929",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Pod Security Policies were Kubernetes rules..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 134,
    "total_tokens": 158
  }
}

What you get by default

  • A single-shot, stateless completion. No persistence, no conversation linkage.
  • Your messages flow through verbatim. Kindo does not prepend a curated system prompt.
  • Tools are only what you list in tools. Kindo does not silently inject hosted tools.

Kindo’s opt-in extensions (curated system prompt, hosted tools, stateful conversations) are available on /v1/responses. See the Chat Actions guide for that surface.

Migrating from llm.kindo.ai

llm.kindo.ai is deprecated. Change the subdomain:

# Old
client = OpenAI(base_url="https://llm.kindo.ai", api_key="...")


# New
client = OpenAI(base_url="https://api.kindo.ai/v1", api_key="...")

The request and response bodies are identical. If you previously sent the bare api-key: header, use Authorization: Bearer for api.kindo.ai.

Next steps