Disallow Prompt Training

Ensure your prompts and responses are never used by providers to train their models.

Enable it

{
  "providerOptions": {
    "gateway": {
      "disallowPromptTraining": true
    }
  }
}

Relationship to ZDR

Disallow prompt training is a subset of Zero Data Retention. All ZDR-compliant providers also disallow prompt training, but more providers disallow training than offer full ZDR.

Filter	Coverage
No-train only	The broader set: every provider that contractually disallows prompt training.
ZDR (includes no-train)	A subset of those: providers that also guarantee zero data retention.

Use disallowPromptTraining when you care about IP protection but don’t need full data deletion guarantees.

No-train verified providers

All ZDR providers plus: OpenAI, Google, Cohere, Perplexity, xAI.

See the full list at GET /api/gateway/compliance.

Routing behavior

Same as ZDR: operators are skipped. Only direct provider calls to verified no-train providers.

Team-wide no-train lives on the Team.noTrainEnabled column. There is no self-serve API for it today: contact Tangle and we set it on your team record.

Zero Data Retention Guardrails