Frequently asked questions
Direct answers about model access, migration, pricing, privacy, and troubleshooting.
Gateway and access
Can I self-host Lazu?
Lazu is offered as a hosted service at lazu.ai. If you need a dedicated or on-premise deployment, contact us and we will walk through the options.
How to migrate from OpenAI?
Change two lines: set base_url from https://api.openai.com/v1 to https://api.lazu.ai/v1, then replace api_key with your Lazu key. Your application code can keep using the official OpenAI Python, JavaScript, or Go SDKs.
Are streaming responses supported?
Yes. Chat completion endpoints support SSE streaming with stream: true, matching OpenAI-compatible behavior.
Is the native Anthropic API supported?
Yes. In addition to OpenAI-compatible /v1/chat/completions, Lazu exposes /v1/messages for Anthropic-compatible requests using x-api-key and anthropic-version headers. Extended Thinking, Prompt Caching, and Tool Use are supported through that path.
Models and providers
How many models are supported?
Lazu exposes the live token-scoped model catalog from GET /api/models/catalog. Current first-class provider families are OpenAI, Anthropic, Google Gemini, and xAI.
Which upstream providers are supported?
Lazu supports OpenAI, Anthropic, Google Gemini, xAI, and custom OpenAI-compatible upstream channels. The console model list and changelog are the source of truth for newly added models.
Can I use Claude and GPT-4 directly from China?
Yes. Use the Lazu endpoint at https://api.lazu.ai and connect directly from domestic IP addresses without a VPN or proxy. Production latency figures should be checked against the live monitoring dashboard.
Pricing and billing
How is pricing calculated?
Pricing follows upstream token usage: input tokens, output tokens, and cache tokens are accounted for separately where the provider exposes them. There is no monthly fee and no minimum spend.
Which payment methods are supported?
Lazu supports online recharge through Stripe.
How can I monitor usage and cost?
The console provides usage dashboards by day, week, and month, with breakdowns by model, endpoint, and token type. Every request includes an x-request-id that can be searched in the logs page.
Privacy and limits
How is data privacy protected?
Chat requests and responses are not stored. Billing keeps request metadata only — timestamp, token counts, status code and request_id. Async media and Studio jobs are the exception: the job input is persisted while the job runs so it can be retried and audited, and you can delete finished jobs.
What are the rate limits?
Rate limits depend on the model, account level, and upstream channel capacity. You can inspect live usage and limits in the console. For higher RPM or TPM, contact the administrator or business support.
How should I troubleshoot errors?
Every response includes an x-request-id header. Search that ID in the console logs to see request time, selected upstream channel, upstream status, token billing details, and any available error stack.