Native APIs and setup
Connect through native model APIs with your endpoint and key
Use the native API for your selected model: OpenAI Responses, Chat Completions, Anthropic Messages, or Gemini GenerateContent. Set the Base URL, API key, and model ID in the matching SDK or client, then send your first request.
Connect with the model’s native SDK
Set the endpoint and API key in an SDK or client that supports your model’s native API.
- Your model’s SDK or matching client lets you set its Base URL and API key.
- You want to choose models and service tiers from the current XiuAI catalog.
- You can test one request and check it in Usage before production use.
Choose the native API for your model
Each model uses its native API. Match the Base URL and request path to both the model and the client or SDK.
responses
OpenAI Responses
- Base URL
- https://router-api.xiu.ai/v1
- Request path
- /responses
Use with models that natively support Responses, through Codex, OpenAI SDKs, or applications built on Responses.
Use it for stateless model requests. Stored conversations, background mode, web search, and file search still require a service that provides those features.
messages
Anthropic Messages
- Base URL
- https://router-api.xiu.ai
- Request path
- /v1/messages
Use with Claude Code, Anthropic SDKs, and Claude-native clients that send Messages requests.
Use it for Messages model requests. Hosted server tools, Message Batches, and Files remain Anthropic platform features.
chat
OpenAI Chat Completions
- Base URL
- https://router-api.xiu.ai/v1
- Request path
- /chat/completions
Use with models that natively support Chat Completions, through OpenAI SDKs, matching clients, or custom-model integrations.
Tool calling, streaming, and client-specific agent behavior depend on the client and selected model. Confirm them with the target task.
gemini
Gemini GenerateContent
- Base URL
- https://router-api.xiu.ai
- Request path
- /v1beta/models/YOUR_MODEL_ID:generateContent
Use with Gemini SDKs and clients that require the native Gemini GenerateContent request format.
The model ID is part of the request path, and the Base URL differs from OpenAI SDKs. Do not add /v1 unless the matching guide shows it.
Choose in three steps
Choose your model and its native API, configure the matching client, then test one request.
- 1
Identify the model’s native API
Choose a client that supports the model’s Responses, Chat Completions, Anthropic Messages, or Gemini GenerateContent API.
- 2
Confirm the model and service tier
Use the current Models and pricing page for the exact model ID, declared endpoint types, tier, and unit rates.
- 3
Verify one real request
Create a scoped key, send a small request, and confirm the model, tier, tokens, status, and recorded cost in Usage.