Skip to content
Kindo Kindo Docs

First API Call

This quickstart walks you through making your first API call to Kindo. By the end, you will have sent a request to the Inference API and received a model response.

Prerequisites

  • A Kindo account (SaaS or self-hosted)
  • An API key (see below)
  • curl or any HTTP client

Get Your API Key

  1. Sign in to the Kindo Terminal.
  2. Click the gear icon (top right) to open Settings.
  3. Navigate to API.
  4. Copy your API key. Keep it secure — treat it like a password.

Send a Chat Request

The chat completions endpoint is OpenAI-compatible and lives on llm.kindo.ai. It accepts the standard Authorization: Bearer header:

Terminal window
curl -X POST https://llm.kindo.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "messages": [
      {
        "role": "user",
        "content": "What are the top 3 cloud security best practices?"
      }
    ]
  }'

Replace YOUR_API_KEY with the key from your Settings page. For self-hosted installations, replace llm.kindo.ai with your inference endpoint.

Response Format

The API returns a standard chat completion response:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Here are the top 3 cloud security best practices..."
      }
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 200,
    "total_tokens": 215
  }
}

Run an Agent via API

Agent endpoints live on api.kindo.ai and use the x-api-key header:

Terminal window
curl -X POST https://api.kindo.ai/v1/agents/YOUR_AGENT_ID/run \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "input": "Run the daily security scan"
  }'

Available Models

View the models available to your organization. This endpoint lives on api.kindo.ai and returns the standard OpenAI models-list format:

Terminal window
curl https://api.kindo.ai/v1/models \
  -H "x-api-key: YOUR_API_KEY"

Response:

{
  "object": "list",
  "data": [
    {
      "id": "claude-sonnet-4-5-20250929",
      "object": "model",
      "created": 0,
      "owned_by": "kindo"
    }
  ]
}

Use the id value as the model parameter in chat completion requests. You can also find exact model names under Settings > Kindo API > Available Models.

Tips

  • Rate limits — API requests are subject to your organization’s rate limits and credit balance.
  • DLP applies — The same Data Loss Prevention filters that protect chat also apply to API requests.
  • Audit logging — All API calls are logged in your organization’s audit trail.

Next Steps