# Create scores URL: https://docs.hanzo.ai/docs/openapi/eval/post-eval-scores > Files one score event for the caller's org and answers 201 with it. `POST /v1/eval/scores` > [Eval →](https://docs.hanzo.ai/docs/openapi/eval) · [All API references →](https://docs.hanzo.ai/docs/openapi) · [Get started →](https://docs.hanzo.ai/docs/guides) | | | | ------------- | -------------------------------------- | | **Address** | `https://api.hanzo.ai/v1/eval/scores` | | **Method** | `POST` | | **Operation** | `post_eval_scores` | | **Auth** | `Authorization: Bearer $HANZO_API_KEY` | Files one score event for the caller's org and answers 201 with it. This is how human review and out-of-band graders land beside the automatic ones: name the score, give it a value (or a stringValue for a categorical label), and attach it to a trace, a run, a dataset example, or any combination. Scores are validated fail-closed. A value must be FINITE — NaN and Inf are 400 — and if the org has declared a rubric for this name, that rubric decides the type and the value must satisfy it: inside the numeric bounds, or one of the allowed categories. A caller cannot override the declared type by sending a different dataType. A score is TELEMETRY, not metadata, so it needs the datastore: a deployment with none wired answers 503 rather than accepting a score it cannot persist. Requires a validated principal; 401 without one, and the org is stamped from the validated claim rather than read off the body. ## Request 9 fields, body `application/json` (required). | Field | In | Type | Required | Description | | --------------- | ---- | --------------- | -------- | ------------------------------------------------------------------------------------- | | `comment` | body | string | — | Comment is the grader's reasoning, truncated at 2000 characters. | | `dataType` | body | string | — | DataType is NUMERIC, CATEGORICAL or BOOLEAN. | | `datasetItemId` | body | string | — | ItemID attaches the score to one graded example. | | `datasetName` | body | string | — | Dataset attaches the score to one dataset. | | `name` | body | string | yes | Name is the score name. | | `runName` | body | string | — | RunName attaches the score to one run. | | `stringValue` | body | string | — | StringValue is the label of a CATEGORICAL score, which must be one the rubric allows. | | `traceId` | body | string | — | TraceID attaches the score to one model call. | | `value` | body | number (double) | — | Value is the numeric score, which must be finite: NaN and Inf are refused. | ## Response | Status | Body | Meaning | | --------- | --------------- | ------- | | `201` | eval.scoreView | created | | `default` | problem-details | refused | `201` body — 9 fields. | Field | In | Type | Always | Description | | ------------- | ---- | --------------- | ------ | ------------------------------------------------------------------------ | | `comment` | body | string | — | Comment is the grader's reasoning, truncated at 2000 characters. | | `dataType` | body | string | — | DataType is NUMERIC, CATEGORICAL or BOOLEAN. | | `id` | body | string | — | ID is the score event's handle. | | `name` | body | string | — | Name is the score name, which a rubric of the same name governs. | | `runName` | body | string | — | RunName is the run this score was recorded under, when it came from one. | | `stringValue` | body | string | — | StringValue is the label of a CATEGORICAL score. | | `timestamp` | body | string | — | Timestamp is when the score was recorded. | | `traceId` | body | string | — | TraceID is the model call this score grades, when it grades one. | | `value` | body | number (double) | — | Value is the numeric score; for BOOLEAN it is 0 or 1. | Failure carries the platform error shape — see [Errors](https://docs.hanzo.ai/docs/errors). ## Examples **CLI** ```bash hanzo eval scores create --name ``` **SDK** **.ts** ```ts import { Configuration, EvalApi } from 'hanzoai'; const api = new EvalApi(new Configuration({ accessToken: process.env.HANZO_API_KEY })); const { data } = await api.postEvalScores({ name: "" }); ``` **.py** ```python from hanzoai.cloud import ApiClient, Configuration from hanzoai.cloud.api import EvalApi client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"])) result = EvalApi(client).post_eval_scores(name="") ``` **.go** ```go cfg := hanzoai.NewConfiguration() cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY")) client := hanzoai.NewAPIClient(cfg) resp, _, err := client.EvalAPI.PostEvalScores(context.Background()).Execute() if err != nil { return err } ``` **.rs** ```rust use hanzo_client::apis::{configuration::Configuration, eval_api}; let mut cfg = Configuration::new(); cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok(); let result = eval_api::post_eval_scores(&cfg, Default::default()).await?; ``` **.java** ```java import ai.hanzo.cloud.ApiClient; import ai.hanzo.cloud.api.EvalApi; ApiClient client = new ApiClient(); client.setBearerToken(System.getenv("HANZO_API_KEY")); var result = new EvalApi(client).postEvalScores(); ``` **HTTP** ```bash curl -X POST https://api.hanzo.ai/v1/eval/scores \ -H "Authorization: Bearer $HANZO_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "name": "" }' ``` **MCP** MCP reaches **eval** through the `eval` tool, which names its 16 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": "list_eval_datasets" } } }' ``` --- [Eval API](https://docs.hanzo.ai/docs/openapi/eval) · [All Hanzo APIs](https://docs.hanzo.ai/docs/openapi) · [Interactive reference](https://docs.hanzo.ai/docs/openapi/reference)