zable

Integrations

Quickstart

Connect your editor, chat interface or backend with a base URL, API key and model ID. Start with a small request and verify the result in Usage.

Base URL

Use this Base URL in an OpenAI-compatible client. It already includes /v1; do not add it twice.

Base URLhttps://api.zableai.com/v1
Chat completions URLhttps://api.zableai.com/v1/chat/completions
Quickstart →

API

Model support varies by tool. Check context limits, streaming and tool calling for your chosen model before running a large task.

  1. Create an API key

    Create a key for an access group, then select a model available to that group.

    API keys ↗

  2. Connect your tool

    Base URL: https://api.zableai.com/v1

  3. Choose your model

Connection example
const response = await fetch("https://api.zableai.com/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${process.env.ZABLE_API_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "kimi-k2.7-code",
    messages: [{ role: "user", content: "Hello!" }]
  })
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Before running these examples, set ZABLE_API_KEY in your terminal or server environment. The curl example uses Bash syntax. Choose a model available to your API key’s access group.

Send a test request

Check your response and credit usage in your workspace.

curl 'https://api.zableai.com/v1/chat/completions' \
  -H "Authorization: Bearer $ZABLE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "kimi-k2.7-code",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Keep API keys private. Never include them in browser code or public repositories.