# Mercury Decide

> Mercury Decide is Inception's structured decision model. Send application state and typed questions (noul / choice / score) and get back a choice, a score, or a yes/no answer, each with a calibrated probability taken straight from the model rather than written out as text, so no output tokens are generated. It answers up to 14 decisions per second, which is fast enough to run on every case and escalate only the unsure ones. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).

**ID**: `inception/mercury-decide`  
**Creator**: inception  
**Category**: text  
**Context**: 33K tokens  
**Input**: $0  
**Output**: $0  
**Released**: 2026-09-30  
**Web page**: https://anyrouter.dev/model/inception/mercury-decide

**Input modalities**: text  
**Output modalities**: text  

**Capabilities**: systemone

**Supported parameters**: state, model, questions

**Aliases**: `inception/mercury-decide:free`

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/decisions`

```bash
curl https://anyrouter.dev/api/v1/decisions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "state": "Help! My payouts have been failing for 3 days.",
  "model": "inception/mercury-decide",
  "questions": {
    "is_urgent": {
      "type": "noul",
      "instructions": "Does this convey urgency?"
    }
  }
}'
```

Decisions is not chat: send `state` and typed `questions` (noul / choice / score). Requires a BYOK key for TypeSafe, LLM Gateway, Vercel AI Gateway, AIHubMix, AutoJev, or Fastino.

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| openrouter-byok | $0 | $0 |

## Source

- Upstream docs: https://openrouter.ai/inception/mercury-decide:free