# Model Evals

Source: https://opvs.ai/docs/api/model-evals

## `GET` /api/v1/factory/model-evals/by-engine

**Get Model Evals By Engine**

Return the brand's run ledger grouped by tool, exact model and task type.

**Parameters**

- `window` (query, string, optional)
- `task_type` (query, any, optional)

```bash
curl -X GET 'https://app.opvs.ai/api/v1/factory/model-evals/by-engine' \
  -H 'Authorization: Bearer <token>'
```

```python
import httpx

resp = httpx.get(
    "https://app.opvs.ai/api/v1/factory/model-evals/by-engine",
    headers={"Authorization": "Bearer <token>"},
)
resp.raise_for_status()
print(resp.json())
```

```javascript
const resp = await fetch("https://app.opvs.ai/api/v1/factory/model-evals/by-engine", {
  method: "GET",
  headers: { "Authorization": "Bearer <token>" }
});
const data = await resp.json();
console.log(data);
```

```go
package main

import (
	"net/http"
)

func main() {
	req, _ := http.NewRequest("GET", "https://app.opvs.ai/api/v1/factory/model-evals/by-engine", nil)
	req.Header.Set("Authorization", "Bearer <token>")
	resp, _ := http.DefaultClient.Do(req)
	defer resp.Body.Close()
}
```

**Responses**

- `200` — Successful Response
- `422` — Validation Error

## `GET` /api/v1/factory/model-evals

**Get Model Evals**

The brand's private model-eval dashboard read.

**Parameters**

- `task_type` (query, any, optional) — Narrow to one routing key (e.g. 'coding'); omit for all
- `min_runs` (query, integer, optional) — Hide models with fewer than this many runs (too little history)
- `format` (query, any, optional) — Response format: yaml | md (default JSON)

```bash
curl -X GET 'https://app.opvs.ai/api/v1/factory/model-evals' \
  -H 'Authorization: Bearer <token>'
```

```python
import httpx

resp = httpx.get(
    "https://app.opvs.ai/api/v1/factory/model-evals",
    headers={"Authorization": "Bearer <token>"},
)
resp.raise_for_status()
print(resp.json())
```

```javascript
const resp = await fetch("https://app.opvs.ai/api/v1/factory/model-evals", {
  method: "GET",
  headers: { "Authorization": "Bearer <token>" }
});
const data = await resp.json();
console.log(data);
```

```go
package main

import (
	"net/http"
)

func main() {
	req, _ := http.NewRequest("GET", "https://app.opvs.ai/api/v1/factory/model-evals", nil)
	req.Header.Set("Authorization", "Bearer <token>")
	resp, _ := http.DefaultClient.Do(req)
	defer resp.Body.Close()
}
```

**Responses**

- `200` — Successful Response
- `422` — Validation Error

## Get Model Evals By Engine

`GET https://app.opvs.ai/api/v1/factory/model-evals/by-engine`

Also as: MCP `tool_call software-factory.getModelEvalsByEngine` · skill `software-factory`

Return the brand's run ledger grouped by tool, exact model and task type.

| Code | When | What to do |
| --- | --- | --- |
| 422 | Validation Error |  |

## Get Model Evals

`GET https://app.opvs.ai/api/v1/factory/model-evals`

Also as: MCP `tool_call software-factory.getModelEvals` · skill `software-factory`

The brand's private model-eval dashboard read.

| Code | When | What to do |
| --- | --- | --- |
| 422 | Validation Error |  |