SegmindSegmind / Docs

Random Seed

The seed parameter controls the randomness of model outputs. Here is how it works across the Segmind platform:

Seed Behavior

Seed ValueBehavior
-1The system generates a random seed automatically. The random seed used is returned in the response header for reproducibility.
Any positive integer (e.g., 42, 12345)Deterministic output. Using the same seed with identical parameters will produce the same result.
Omitted / not providedBehavior is model-dependent. Most models will treat this as random, but some may use a model-specific default.

Important: Some model documentation pages may show a default seed value (e.g., 12345) in the API parameter list. This is a placeholder example, not the actual default used when the parameter is omitted. To guarantee random results every time, explicitly set seed: -1 in your request.

When to Use

  • For consistent, reproducible outputs: Provide a specific seed value (e.g., seed: 42). The same prompt + seed + parameters will produce the same output.
  • For varied results each time: Set seed: -1 to explicitly request random generation.
  • For A/B testing or debugging: Use a fixed seed to isolate the effect of other parameter changes.

This approach works across model APIs, model playground (UI), PixelFlow UI, and PixelFlow APIs.

On this page