Source: How to make your completions outputs consistent with the new seed parameter (OpenAI Cookbook)
OpenAI Cookbook notebook introducing the beta seed parameter and system_fingerprint, and what 'mostly deterministic' means for the API.
Contents
- What: official cookbook notebook (now marked archived)
- Author: OpenAI
- Date: late 2023 (written against the November 2023
-1106models); accessed 2026-11-14 - Original: Reproducible outputs with the seed parameter
Summary
Explains OpenAI’s best-effort determinism feature: send the same integer seed and the same parameters, and compare system_fingerprint across responses to detect backend changes that would break reproducibility.
Key claims
seedrequests best-effort deterministic sampling; outputs should mostly match, but determinism is not guaranteed.- Conditions: same seed, same prompt and parameters (temperature, top_p, max_tokens, …), and matching
system_fingerprint. system_fingerprintidentifies the backend configuration (weights, infrastructure, settings); OpenAI expects it to change a few times a year.- Even with all conditions met, outputs can occasionally differ because of inherent model non-determinism.
- At launch the feature was beta and limited to
gpt-4-1106-previewandgpt-3.5-turbo-1106. - In the notebook’s example, seeded temperature-0 runs were much closer to each other than unseeded ones, but not reported as identical.