XiuRouter FAQ: APIs, Pricing, Usage and Data Privacy

Codex uses Responses; Claude Code uses Anthropic Messages; tools limited to OpenAI-compatible chat use Chat Completions; native Gemini SDKs use GenerateContent. The client request format determines the protocol, not the model brand.

A key can be used for the models and service tier it is allowed to access, but each protocol also depends on the endpoint types currently declared by the target model. Confirm the model scope when creating the key, then verify with a small request on the matching protocol.

Use router-api.xiu.ai for new integrations. OpenAI Chat Completions and Responses use https://router-api.xiu.ai/v1; Anthropic Messages and Gemini GenerateContent use https://router-api.xiu.ai. router.xiu.ai hosts the website and console.

Sign in, open API Keys, and create a key with a service tier, model scope, credit limit, and expiry. Copy a model ID, send one short request, then confirm the model, tier, tokens, status, and cost in Usage.

XiuRouter provides APIs for Claude, GPT and other models. Before calling, copy a currently available model ID and confirm key access, API format and price. Supporting a request format does not make every model from its developer available.

A service tier determines the current model and price source. Its name is not a speed, quality, reliability, failover, or SLA promise. Evaluate the target model with a real request and its resulting usage record.

Copy the exact model ID from the current Models and pricing page. Clients that support discovery can also read /v1/models. Do not construct an ID from a marketing name.

Catalog visibility means the current public catalog can describe the model. A request still depends on the protocol, key status, model scope, service tier, balance, and the upstream response at that moment. Check the request record rather than treating visibility as permanent availability.

View rates by model and service tier on Models and pricing. Use /api/pricing for machine-readable current pricing.

They are separate per-1M-token rates for each usage type. Only usage produced by the request is billed, and models billed per request are marked separately.

A reference price is a comparison point for the same model, not the XiuRouter rate. Your recorded cost uses the model and service tier that handled the request plus the applicable input, output, and cache rates.

Each service tier has its own model availability and rates. If a key uses automatic routing or cross-tier retry, the tier that handles the request determines the price. Check the actual tier and recorded cost in Usage.

Find the request in Usage by API key, time, or request ID. Check the model, service tier, input, output, cache usage, status, and recorded cost. Models and pricing shows the unit rates; Usage shows what the request used.

XiuRouter does not store prompts, message history, files, images or model responses. Conversation content is processed and transmitted solely to complete the model request.

Usage records include model identifiers, timestamps, token counts, cache metering, costs, outcomes and latency. Usage statistics and model performance data are retained long term for billing, usage history and performance analysis.

XiuRouter does not use model conversations for training or sell any user data.

XiuRouter’s upstream access policy permits only services operated by model developers themselves.

Model developers process requests under the policies for their services, including training use, security logs, retention and caching. Privacy support can provide information about the terms applicable to specific models and features.

Requests for access, correction, export or deletion of personal information may be submitted to contact@xiu.ai, identifying the account, information and requested action. We verify identity or authorization as needed and respond under applicable law.

Confirm the authentication header matches the protocol, the key is active and unexpired, the model is inside its scope, the service tier allows it, and the account has balance. Do not repeatedly create or rotate keys while the outcome is unclear.

Different SDKs append different paths. A common failure is putting /v1 in the Base URL when the client adds another /v1, or mixing Responses, Messages, Chat, and Gemini routes. Check the final request URL against the protocol page.

Copy the model ID again from the current pricing page, confirm the target tier still lists it, and check the key’s model scope. If the catalog or upstream state changed, choose a currently available combination and send one small request.

Check Usage first to see whether the previous request was recorded and charged before retrying. Keep the request ID and partial output; an incomplete client response does not prove the request never happened.

The text path may be working while the client-specific tool protocol, streaming events, or the selected model’s tool ability does not meet the task. Check the client guide’s boundary and verify with a smaller tool task.

The current Codex path uses OpenAI Responses and selects XiuRouter through a local provider configuration. It affects new local Codex tasks, not cloud ChatGPT chats.

Claude Code speaks Anthropic Messages and appends /v1/messages itself, so its gateway root differs from the /v1 Base URL used by OpenAI SDKs. Follow the current Claude Code guide.

No. The current Base URL override mainly affects the relevant OpenAI-compatible model path. Cursor-specific models, Tab completion, and other proprietary features can remain on Cursor’s service. Ask working does not automatically prove Agent file edits work.

First confirm it accepts a custom Base URL and API key, then identify whether it sends Responses, Messages, Chat Completions, or Gemini requests. Even then, verify one real request with the target model and reconcile its usage record.

Confirm the final request URL, authentication header, model ID, service tier, and current rate. Send one small request, reconcile status, tokens, and cost in usage records, then add application handling for timeouts, limits, and upstream failures.

No. The pricing page shows the current catalog and rates; it does not guarantee uptime, latency, output consistency, or failover. Plan retries, fallback behavior, monitoring, and spend limits in your application.

XiuRouter is a usage-billed model API for applications and agents. ChatGPT and Claude subscriptions cover their own chat interfaces and account features and generally do not include API credit for other applications.

Support requests should include the time, request ID, client, protocol, model ID, service tier and redacted error details, excluding conversation content and complete API keys. The name or masked digest displayed in the console is sufficient to identify a key.