# Create runs

URL: https://docs.hanzo.ai/docs/openapi/benchmark/post-benchmark-runs

> Admits and queues a benchmark run against a model or your own endpoint, and answers 202 with the receipt.

`POST /v1/benchmark/runs`

> [Benchmark →](https://docs.hanzo.ai/docs/openapi/benchmark) · [All API references →](https://docs.hanzo.ai/docs/openapi) · [Get started →](https://docs.hanzo.ai/docs/guides)

|               |                                          |
| ------------- | ---------------------------------------- |
| **Address**   | `https://api.hanzo.ai/v1/benchmark/runs` |
| **Method**    | `POST`                                   |
| **Operation** | `post_benchmark_runs`                    |
| **Auth**      | `Authorization: Bearer $HANZO_API_KEY`   |

Admits and queues a benchmark run against a model or your own endpoint, and
answers 202 with the receipt.

It is an ADMISSION, not a result: the work is done by the harness afterwards and
the numbers appear on the leaderboard as it completes them.

Any signed-in caller may ask; a caller with no verified principal is refused
401\. The receipt names the caller's verified org and user — nothing in the
body names either — and stores nothing.

Cost is bounded by the store rather than by a quota: attempts are append-only and
keyed by (benchmark, item, model), so an (item, model) pair already attempted is
skipped instead of re-spent, and re-queuing the same run is close to free.

Validation is up front and total — a request with neither model nor endpoint is a
400, one with no benchmarks is a 400, and any benchmark id outside the catalog is
a 422 naming exactly which ids were unknown, so a typo never silently queues a
partial run.

## Request

4 fields, body `application/json` (required).

| Field        | In   | Type            | Required | Description                                                                                    |
| ------------ | ---- | --------------- | -------- | ---------------------------------------------------------------------------------------------- |
| `attempts`   | body | integer (int64) | —        | Attempts is how many times to try each item; the harness's default applies when it is omitted. |
| `benchmarks` | body | string\[]       | yes      | Benchmarks are the catalog ids to run.                                                         |
| `endpoint`   | body | string          | —        | Endpoint is your own chat-completions URL, for benchmarking a model this arena does not host.  |
| `model`      | body | string          | —        | Model is the catalog model id to run.                                                          |

## Response

| Status    | Body                | Meaning  |
| --------- | ------------------- | -------- |
| `202`     | benchmark.admission | accepted |
| `default` | problem-details     | refused  |

`202` body — 7 fields.

| Field        | In   | Type      | Always | Description                                                        |
| ------------ | ---- | --------- | ------ | ------------------------------------------------------------------ |
| `benchmarks` | body | string\[] | —      | Benchmarks are the catalog ids admitted.                           |
| `by`         | body | string    | —      | By is the verified user who asked for it.                          |
| `endpoint`   | body | string    | —      | Endpoint is the caller's own endpoint the run targets.             |
| `model`      | body | string    | —      | Model is the catalog model the run targets.                        |
| `note`       | body | string    | —      | Note explains what admission does and does not promise.            |
| `org`        | body | string    | —      | Org is the org the run is admitted for: the caller's verified org. |
| `status`     | body | string    | —      | Status is "queued": the run is admitted, not finished.             |

Failure carries the platform error shape — see [Errors](https://docs.hanzo.ai/docs/errors).

## Examples

**CLI**

```bash
hanzo benchmark runs --benchmarks '["<benchmarks>"]'
```

**SDK**

**.ts**

```ts
import { Configuration, BenchmarkApi } from 'hanzoai';

const api = new BenchmarkApi(new Configuration({ accessToken: process.env.HANZO_API_KEY }));
const { data } = await api.postBenchmarkRuns({ benchmarks: ["<benchmarks>"] });
```

**.py**

```python
from hanzoai.cloud import ApiClient, Configuration
from hanzoai.cloud.api import BenchmarkApi

client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"]))
result = BenchmarkApi(client).post_benchmark_runs(benchmarks=["<benchmarks>"])
```

**.go**

```go
cfg := hanzoai.NewConfiguration()
cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY"))
client := hanzoai.NewAPIClient(cfg)

resp, _, err := client.BenchmarkAPI.PostBenchmarkRuns(context.Background()).Execute()
if err != nil {
	return err
}
```

**.rs**

```rust
use hanzo_client::apis::{configuration::Configuration, benchmark_api};

let mut cfg = Configuration::new();
cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok();

let result = benchmark_api::post_benchmark_runs(&cfg, Default::default()).await?;
```

**.java**

```java
import ai.hanzo.cloud.ApiClient;
import ai.hanzo.cloud.api.BenchmarkApi;

ApiClient client = new ApiClient();
client.setBearerToken(System.getenv("HANZO_API_KEY"));

var result = new BenchmarkApi(client).postBenchmarkRuns();
```

**HTTP**

```bash
curl -X POST https://api.hanzo.ai/v1/benchmark/runs \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
       "benchmarks": [
         "<benchmarks>"
       ]
     }'
```

**MCP**

MCP reaches **benchmark** through the `benchmark` tool, which names its 9 operations with its own verbs — this one among them, under a name only MCP declares. `describe` explains any of them:

```bash
curl -X POST https://api.hanzo.ai/v1/mcp \
  -H "Content-Type: application/json" \
  -d '{
       "jsonrpc": "2.0",
       "id": 1,
       "method": "tools/call",
       "params": {
         "name": "describe",
         "arguments": {
           "op": "get_benchmark_catalog"
         }
       }
     }'
```

---

[Benchmark API](https://docs.hanzo.ai/docs/openapi/benchmark) · [All Hanzo APIs](https://docs.hanzo.ai/docs/openapi) · [Interactive reference](https://docs.hanzo.ai/docs/openapi/reference)