Append runs to an experiment

Append new runs to an existing experiment.

Payload Requirements

• Provide between 1 and 1000 runs in experiment_runs.
• Each run must include:
  • output -- model/task output for the run
  • example_id -- the ID of an existing example in the dataset, required only when the experiment is associated with a dataset
  • You may include any additional fields per run that can be used for analysis or filtering. For example: model, latency_ms, temperature, prompt, tool_calls, etc.

Valid example

{
  "experiment_runs": [
    {"example_id": "example_001", "output": "4", "model": "gpt-4o-mini"}
  ]
}

Invalid example (missing required output field)

{
  "experiment_runs": [
    {"example_id": "example_001"}
  ]
}

<Note>This endpoint is in beta, read more here.</Note>