# LLM Router API

Run prompts through an LLM of your choice and get the answer, model, provider, finish reason and token counts for each.

**Pricing:** $0.004 per answer

**Endpoint:** `POST /v1/data/llm/route/run`

**Auth:** `Authorization: Bearer mk_live_...`

## Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `prompts` | array | Yes | One or more prompts. One request reads them all. |
| `model` | string | No | Model. |

## Example

`?wait=true` holds the request open until the run finishes (up to 60s) and returns the rows inline: one request, no polling.

```bash
curl -X POST "https://api.mindcase.co/v1/data/llm/route/run?wait=true" \
  -H "Authorization: Bearer mk_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"params":{"prompts":["..."]}}'
```

```python
import requests

resp = requests.post(
    "https://api.mindcase.co/v1/data/llm/route/run",
    params={"wait": "true"},
    headers={"Authorization": "Bearer mk_live_YOUR_API_KEY"},
    json={"params": {
    "prompts": [
        "..."
    ]
}},
)
rows = resp.json()["data"]
```

## Longer runs

If the run is still going at the 60s ceiling you get back `{ job_id, status: "running" }` instead of rows (same if the result is over 100 rows; those come back `truncated`). Poll with that `job_id`:

```bash
# 1) check status
curl https://api.mindcase.co/v1/jobs/JOB_ID \
  -H "Authorization: Bearer mk_live_YOUR_API_KEY"

# 2) when status == completed, fetch the rows
curl https://api.mindcase.co/v1/jobs/JOB_ID/results \
  -H "Authorization: Bearer mk_live_YOUR_API_KEY"
```

Full API reference (auth, jobs, balance, SDKs, MCP): https://mindcase.co/skills.md

## Response columns

| Field | Display name | Type |
|-------|--------------|------|
| `id` | ID | text |
| `prompt` | Prompt | text |
| `answer` | Answer | text |
| `model` | Model | text |
| `provider` | Provider | text |
| `finishReason` | Finish Reason | text |
| `promptTokens` | Prompt Tokens | number |
| `completionTokens` | Completion Tokens | number |
| `totalTokens` | Total Tokens | number |
| `reasoningTokens` | Reasoning Tokens | number |
| `createdAt` | Created At | datetime |