Skip to main content

​
Prerequisites

​
Option 1: cURL

curl -X POST https://api.a21e.com/v1/rpc \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "method": "intent.submit",
    "params": {
      "input": "Explain the builder pattern in TypeScript with a practical example",
      "auto_execute": true
    }
  }'

​
Option 2: OpenAI SDK (drop-in)

If you already use the OpenAI SDK, point it at a21e: 
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_A21E_API_KEY",
    base_url="https://api.a21e.com/v1",
)

response = client.chat.completions.create(
    model="auto",
    messages=[
        {"role": "user", "content": "Write a retry decorator with exponential backoff"}
    ],
)

print(response.choices[0].message.content)
The model parameter is mapped to a21e’s model tier system. Use "auto" to let a21e pick the best model, or specify "economy", "standard", or "premium".

​
Option 3: Huddle (web interface)

  1. Go to a21e.com/huddle
  2. Type your request in the composer
  3. Choose Single (fast, one model) or Multi (deliberation across models)
  4. Get your response with full context and quality metadata in the sidebar

​
What happens behind the scenes

When you submit an intent, a21e runs a pipeline: Each step is observable — the API returns timing breakdowns, quality scores, and the techniques used.

​
Next steps

Intents guide

Learn how intent submission works, including model tiers, constraints, and follow-ups.

API reference

Full API documentation with interactive playground.

Workspaces

Set up workspaces with repo context, preferences, and personas.

BYOK setup

Bring your own LLM API keys to reduce credit usage.