curl -X POST 'https://api.openai.com/v1/fine_tuning/alpha/graders/run' \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "grader": {
    "type": "string_check",
    "name": "example-name",
    "input": "example-input",
    "reference": "example-reference",
    "operation": "eq"
  },
  "model_sample": "example-model-sample"
}'

# POST /fine_tuning/alpha/graders/run (OpenAI API)
Base URL: https://api.openai.com/v1
Auth: Authorization; OpenAI API key; required.
Request formats: application/json.
Last verified: 2026-10-20

> Run grader

## Critical Gotchas
* The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.
* Audio transcription uploads use multipart form data rather than a JSON request body.

## cURL
curl -X POST 'https://api.openai.com/v1/fine_tuning/alpha/graders/run' \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "grader": {
    "type": "string_check",
    "name": "example-name",
    "input": "example-input",
    "reference": "example-reference",
    "operation": "eq"
  },
  "model_sample": "example-model-sample"
}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| grader | body | object | Yes | The grader used for the fine-tuning job. |
| model_sample | body | string | Yes | The model sample to be evaluated. This value will be used to populate the `sa... |
| item | body | object | No | The dataset item provided to the grader. This will be used to populate the `i... |

## Response example
{"reward":0,"metadata":{"name":"string","type":"string"}}

---
Need an API key? Get one at https://platform.openai.com/api-keys

POST

POST /fine_tuning/alpha/graders/run — OpenAI API

OpenAI API key (required); https://api.openai.com/v1

OpenAI API

Run grader

Base URL: https://api.openai.com/v1
Auth: Authorization: Bearer <OPENAI_API_KEY>
Last verified: 2026-10-20 · upstream hash matched

Actions Try in browser→

Agents: curl -H "Accept: text/markdown" this URL
→ 259 tokens · Vary: Accept

Critical gotchas

The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.

Audio transcription uploads use multipart form data rather than a JSON request body.

cURL

curl -X POST 'https://api.openai.com/v1/fine_tuning/alpha/graders/run' \  -H "Authorization: Bearer $OPENAI_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "grader": {    "type": "string_check",    "name": "example-name",    "input": "example-input",    "reference": "example-reference",    "operation": "eq"  },  "model_sample": "example-model-sample"}'

Parameters

Name	In	Type	Required	Description
grader	body	object	Yes	The grader used for the fine-tuning job.
item	body	object	No	The dataset item provided to the grader. This will be used to populate the `item` namespace. See [the guide](https://developers.openai.com/api/docs/guides/graders) for more details.
model_sample	body	string	Yes	The model sample to be evaluated. This value will be used to populate the `sample` namespace. See [the guide](https://developers.openai.com/api/docs/guides/graders) for more details. The `output_json` variable will be populated if the model sample is a valid JSON string.

Response 200 OK

{
  "reward": 0,
  "metadata": {
    "name": "string",
    "type": "string",
    "errors": {
      "formula_parse_error": true,
      "sample_parse_error": true,
      "truncated_observation_error": true,
      "unresponsive_reward_error": true,
      "invalid_variable_error": true,
      "other_error": true,
      "python_grader_server_error": true,
      "python_grader_server_error_type": "string",
      "python_grader_runtime_error": true,
      "python_grader_runtime_error_details": "string",
      "model_grader_server_error": true,
      "model_grader_refusal_error": true,
      "model_grader_parse_error": true,
      "model_grader_server_error_details": "string"
    },
    "execution_time": 0,
    "scores": {},
    "token_usage": {
      "prompt_tokens": 0,
      "total_tokens": 0,
      "completion_tokens": 0,
      "cached_tokens": 0
    },
    "sampled_model_name": "string"
  },
  "sub_rewards": {},
  "model_grader_token_usage_per_model": {}
}

Get a free OpenAI API key → sponsored

Affiliate link - we may earn a commission, at no extra cost to you.