Supported Providers

XSI selects the path mapping and authentication method automatically from the upstream hostname of each provider key. Clients always use the standard paths of the official protocol (such as /v1/chat/completions and /v1/messages). Azure and Vertex AI are declared with config.provider_type; see Provider Key API.

Native support

ProviderProvider URLSupported protocolsNotes
OpenAIhttps://api.openai.comAll OpenAI endpoints, including Responses WebSocket, Realtime, and LivePaths without /v1 are completed automatically
Azure OpenAI / Azure AIhttps://<resource>.openai.azure.com, etc.Chat, Responses, Embeddings, Images, Audioprovider_type: azure; supports deployment mapping and api-version; use an OpenAI upstream for Realtime connections
Anthropichttps://api.anthropic.comMessages, count_tokens, FilesAlways authenticates with x-api-key
Google Geminihttps://generativelanguage.googleapis.comNative Gemini API; OpenAI-compatible Chat and EmbeddingsNative paths use x-goog-api-key
Google Vertex AIhttps://aiplatform.googleapis.comNative Gemini APIprovider_type: vertex; service account authentication
xAIhttps://api.x.aiChat, Responses, Images, VideosVideo job polling is bound to the account
DeepSeekhttps://api.deepseek.comChat, Responses, Messages, web tools, OCR, TTS (including WebSocket), ASR, Files, balanceSee DeepSeek Full-Suite Integration
Alibaba Cloud Model Studio / DashScopehttps://*.aliyuncs.comChat, Embeddings, Rerank, Responses, Messages, RealtimeRealtime is mapped to /api-ws/v1/realtime automatically
Volcano Engine Arkhttps://ark.cn-beijing.volces.comChat, Responses, Embeddings, Images, MessagesIncludes Coding Plan paths
Baidu Qianfanhttps://*.baidubce.comChat, Responses, Embeddings, Images, Rerank, Messages
Zhipuhttps://open.bigmodel.cn, https://api.z.aiChat, Embeddings, Images, Messages
Moonshothttps://api.moonshot.cnChat, Messages
MiniMaxhttps://api.minimaxi.comChat, Messages
Tencent Cloudhttps://api.lkeap.cloud.tencent.comChat, Messages
LongCathttps://api.longcat.chatChat, Messages
Perplexityhttps://api.perplexity.aiChat
Coherehttps://api.cohere.aiChat, Embeddings (compatibility API)
DeepInfrahttps://api.deepinfra.comChat
Fireworkshttps://api.fireworks.aiChat, Completions, Responses, Messages, Rerank
GitHub Modelshttps://models.github.aiChat
Groq, Cerebras, SiliconFlow, OpenRouter, OllamaTheir official URLsOpenAI-compatible APIBearer authentication; paths forwarded as is
Cloudflare AI Gatewayhttps://gateway.ai.cloudflare.com/...Depends on gateway configurationAuthenticates with cf-aig-authorization

Connecting other compatible services

Any service with an OpenAI-compatible or Anthropic-compatible API (including self-hosted vLLM, SGLang, Ollama, and so on) can be used as a provider:

  • Set Provider to the service's base URL. It may include a path prefix, such as https://llm.internal.example.com/openai; XSI appends the request path to it.
  • OpenAI-style paths are forwarded with Authorization: Bearer; /messages paths use x-api-key.
  • When the provider is a public IP address, XSI automatically adds /v1 to /chat/completions, /embeddings, /responses, and /messages.

Models and pricing

After connecting a provider, the models must also appear in the price list so XSI can bill and map them correctly:

  • The default price list, api/pricing.json, already includes the main models of the GPT, Claude, Grok, DeepSeek, GLM, Kimi, Doubao, and Qwen families.
  • Add other models through the tenant PRICING setting. See Billing and Pricing.
  • Public prices are listed in the model catalog and at GET /x-pricing.