# megachad cua

> Decision model API. Text or live speech plus a schema of questions in; one calibrated answer per field (one of N options, yes/no, or a scale) with a confidence out. The model decides in ~17 ms. Runs on a fine-tuned Qwen 3.8 27B.

megachad cua is a decision model API. Send text or live speech plus a schema of questions; get back one calibrated answer per field, each with a confidence. The model decides in ~17 ms. Each question is one of N options, yes/no, or a scale. It runs on a fine-tuned Qwen 3.8 27B. Use it as the decision step of an agent or app: which on-screen control the user means, which queue a call goes to, whether they confirmed, how urgent a ticket is. It picks; it doesn't write text or reason out loud. Medical use: it routes and structures for clinicians. It doesn't diagnose.

Key: a human signs up at https://megachadcua.com/login?signup=1 ($2 free, no card) and gets a key (`mcc_live_...`). Coding agents: ask your user to paste the key into the `MEGACHAD_API_KEY` env var and read it from there. Never hardcode it, never commit it, never print it. Don't sign up for the user.

Base URL `https://api.megachadcua.com`, auth `Authorization: Bearer $MEGACHAD_API_KEY`. Raw HTTP works from any language with nothing installed; start there:

```bash
curl https://api.megachadcua.com/v1/decide \
  -H "Authorization: Bearer $MEGACHAD_API_KEY" \
  -H "content-type: application/json" \
  -d '{"schema": {"action": {"question": "What should the agent do?", "options": ["Click Sign in", "Scroll down", "Nothing yet"]}}, "text": "take me to sign in"}'
```

Response (200):

```json
{"session_id": "dcd_C8o5VFBm5AH65L7e", "fields": {"action": {"value": "Click Sign in", "confidence": 0.98, "probabilities": {"Click Sign in": 0.98, "Scroll down": 0.012, "Nothing yet": 0.008}}}, "transcript": "take me to sign in", "latency_ms": 112, "model_ms": 15.2, "usage": {"credits": 1}}
```

Pricing: 10¢ per 1,000 decisions, 6¢ a minute of voice.

## Docs

- [API docs](https://megachadcua.com/docs.md): keys, POST /v1/decide, POST /v1/decide/batch, WS /v1/listen, schema, errors, retries and idempotency, limits, SDKs, CLI, MCP
- [Everything in one file](https://megachadcua.com/llms-full.txt): the API docs plus pricing, status and the agent guide
- [Pricing](https://megachadcua.com/pricing.md): credits, free credit, worked examples
- [Status](https://megachadcua.com/status.md): what GET /v1/status and /v1/status/history return
- [OpenAPI 3.1](https://megachadcua.com/openapi.json): POST /v1/decide, POST /v1/decide/batch, GET /v1/status

## Agents

- [Agent guide](https://megachadcua.com/agents.md): coding-agent setup, the runtime decision step, schema design, confidence thresholds, batching, tool definitions (Anthropic, OpenAI)
- [Claude Code skill](https://megachadcua.com/agents/megachad/SKILL.md): save as ~/.claude/skills/megachad/SKILL.md
- [AGENTS.md block](https://megachadcua.com/agents/AGENTS.md): append to a repo's AGENTS.md (Codex, Cursor, Copilot, Gemini CLI, Aider, Windsurf)
- [Cursor rule](https://megachadcua.com/agents/megachad.mdc): save as .cursor/rules/megachad.mdc

## Optional

- [Home](https://megachadcua.com/index.md): what it's for, in short
- [Terms](https://megachadcua.com/terms.md)
- [Privacy](https://megachadcua.com/privacy.md)