Data controls

Turn on zero data retention and no-training routing for your org or a single request, and verify who served each call.

Turn on zero data retention (one call)

The account-wide switch sets three facts in one audited transaction: prompt capture off, require_zdr on, require_no_training on. GET returns enabled (all three hold), partial (switched on but a fact drifted), enforced_at, and models_with_zdr_route (a count of public models still callable). With it on, a model with no zero-retention route is refused with 403 model_not_granted. ZDR is a Pro feature (403 needs_subscription otherwise). What ZDR means and the provider matrix: Data controls.

GET/api/orgs/{org_id}/zero-data-retentionPUT/api/orgs/{org_id}/zero-data-retention
curl -X PUT https://api.experientiallabs.ai/api/orgs/ORG_ID/zero-data-retention \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"enabled": true}'

Provider policy fields

PUT takes a partial document: omitted fields keep their value; null clears a list; null on a boolean is a 400. Every change is audited as provider_policy.set and reaches the gateway within seconds.

FieldEffectPlan
require_zdrOnly zero-retention routes (including routes on your own keys)Pro
require_no_trainingOnly routes whose provider does not train on dataAll
allowed_processing_regionse.g. ["US"]: every route must have reviewed coverage in those regions; disables batchesAll
prompt_cachingfalse stops gateway-side caching and strips cache markersAll
zdr_continuation_storageAllow previous_response_id under ZDR routing (stored by us only)Pro
allowed_providersProvider allowlist by displayed nameEnterprise (403 enterprise_required)

While the account-wide switch is on, lowering require_zdr or require_no_training is 409 zdr_switch_enforced. DELETE removes the policy.

PUT/api/orgs/{org_id}/provider-policyGET/api/orgs/{org_id}/provider-data-controls
curl -X PUT https://api.experientiallabs.ai/api/orgs/ORG_ID/provider-policy \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"require_no_training": true}'

Per request

Add top-level "provider": {"zdr": true} on Chat, Responses or Messages (Anthropic SDK: extra_body), or the X-Gateway-ZDR: true header. It only tightens: the request is judged as if require_zdr were on, answers x-gateway-zdr: true, and is refused with 403 model_not_granted naming provider.zdr when no route qualifies. Pro, unless your org already holds require_zdr. ZDR-routed requests are never captured.

POST/v1/chat/completions
curl -i https://api.experientiallabs.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-6-luna", "provider": {"zdr": true},
       "messages": [{"role": "user", "content": "Hello"}]}'

Check a model before you switch

ReadField
GET /v1/modelsdata_policy: zdr (every route ZDR by default), zdr_on_request, no_training, per-provider rows
GET /api/modelsretention: zdr_all_rungs, zdr_enforceable, not_zdr; filter ?retention=zdr_all_rungs
GET /api/models/{slug}/providerszero_data_retention per route
GET /api/v1/endpoints/zdrPublic list of every route a require_zdr org is served through
GET/api/v1/endpoints/zdrGET/api/models
curl "https://api.experientiallabs.ai/api/models?retention=zdr_all_rungs&limit=50" \
  | jq -r '.models[].model.slug'

Verify who served a request

Headers are stamped after a provider commits, so they name the route that answered. The body carries the same provider beside usage.cost. Look up any request later by its id.

HeaderValue
x-request-idGateway request id
x-gateway-providerProvider that served
x-gateway-zdrWhether that route is zero-retention
x-gateway-route-depthPosition of the serving route (0 = first)
x-gateway-canonical-modelResolved model identity
GET/api/v1/generation
curl -sD - -o /dev/null https://api.experientiallabs.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" \
  -d '{"model": "gpt-6-luna", "messages": [{"role": "user", "content": "Hi"}]}' \
  | grep -i '^x-gateway\|^x-request-id'

Prompt and response storage

capture_prompt_content controls stored prompts, responses and Responses continuations. Turning it off needs Pro (or a grandfathered org); 403 needs_subscription otherwise. The content-free usage ledger (tokens, cost, provider) is always kept. Details on Telemetry.

PUT/api/orgs/{org_id}/telemetry-settings
curl -X PUT https://api.experientiallabs.ai/api/orgs/ORG_ID/telemetry-settings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"capture_prompt_content": false}'