Support Center
We’re here to keep your API online
Reach the right team instantly, follow our self-serve guides, or escalate an incident. Transend AI Support is staffed by engineers who understand multi-provider routing.
Product & Integration
API errors, SDK questions, routing behaviour, or latency investigations.
[email protected]First response within 12 business hours.
Billing & Credits
Invoices, tax documentation, credit grants, or usage disputes.
[email protected]First response within 1 business day.
Enterprise & Partnerships
Custom SLAs, dedicated capacity, or partner integrations.
[email protected]Intro call within 2 business days.
Security & Incidents
Responsible disclosure, key compromise, or urgent incident escalation.
[email protected]24/7 pager coverage, < 1 hour acknowledgement.
Operational Resilience
Pager rotation. We monitor provider latency, fail rates, and credit balances 24/7. Critical incidents trigger a < 5 minute page to our on-call SRE.
Incident channels. Enterprise workspaces receive a private Slack or Teams channel with our reliability engineers for real-time triage.
Post-incident reviews. We publish root-cause analyses within 5 business days and track remediation items in the status dashboard.
Emergency reset. If keys are compromised, rotate credentials from the dashboard or email [email protected] and we can invalidate traffic globally within minutes.
Data handling. All support tickets are scrubbed for prompts before they enter our ticketing system. Sensitive payloads should be shared via encrypted attachments or our secure portal.
Frequently Asked Questions
How does credit billing work?
Credits are billed per-token across any connected model. Usage and spend are visible in the dashboard in near real time. When your balance reaches 10% we automatically alert the billing contacts, giving you time to top up or enable auto-reload.
Can I keep prompts and completions out of Transend AI logs?
Yes. By default we retain only request metadata (latency, token count, provider). Toggle "Ephemeral prompts" in the workspace settings to ensure payloads never persist beyond transient processing, or configure a custom retention window via DPA.
What regions are available for routing?
Transend AI currently operates POPs in us-east, us-west, eu-central, and ap-southeast. Enterprise plans can request dedicated regions or on-premise agents for regulated workloads.
Where can I see platform status?
Visit the Status Dashboard for live uptime metrics and postmortems. You can subscribe to email or Slack notifications from the status page.
Do you support self-hosted or private models?
Yes. Through Private Connectors you can expose models hosted in your own VPC or on-prem cluster while keeping routing, auth, and billing unified through Transend AI. Contact [email protected] to enable the feature.
Self-Serve Resources
Endpoints, SDK examples, and schema changelog.
Live incident feed, historical uptime, and maintenance windows.
Step-by-step guides for migrating from OpenAI, Vertex, and Bedrock.
Encryption, pen-test summaries, and data handling FAQs.