​
Text Series

Model Support Matrix

View the support scope of the text series, typical model families, and recommended entry points by protocol style and capability type.

Chat Completions

POST /v1/chat/completions, suitable for chat, Agents, long-text generation, and multimodal input.

OpenAI Responses

POST /v1/responses, suitable for tool calling, structured outputs, and context continuation.

Claude Native

POST /v1/messages, preserving the Anthropic Messages protocol.

Gemini Native

POST /v1beta/models/{model}:{action} and GET /v1beta/models.

​
Authentication

Most text relay interfaces use a Bearer Token: 
Authorization: Bearer YOUR_API_KEY
The Claude native format also supports: 
x-api-key: YOUR_API_KEY
anthropic-version: 2023-06-01
The Gemini native format also supports: 
x-goog-api-key: YOUR_API_KEY

​
Interface List

MethodPathPageDescription
POST/v1/chat/completionsChat Completions Interface (streaming by default)OpenAI Chat Completions-compatible format, the documentation shows the streaming call by default
POST/v1/chat/completionsChat Completions Interface (non-streaming by default)Non-streaming usage of the same route
POST/v1/completionsText Completions InterfaceLegacy Completions-compatible format
POST/v1/messagesClaude Messages InterfaceAnthropic Messages native protocol
POST/v1/responsesOpenAI Multimodal Responses InterfaceResponses API
POST/v1/responses/compactOpenAI Multimodal Responses InterfaceContext compression
GET/v1/realtimeRealtime InterfaceOpenAI Realtime-compatible WebSocket
GET/v1/modelsModel ListOpenAI/Claude/Gemini-compatible model list
GET/v1/models/{model}Model ListSingle model query
GET/v1beta/modelsGemini Native FormatGemini native model list
POST/v1beta/models/{model}:{action}Gemini Native FormatGemini native inference and image/video-related actions
GET/v1beta/openai/modelsModel ListGemini-compatible model list
POST/pg/chat/completionsChat Completions Interface (non-streaming by default)Playground debugging route, using login session instead of API Key

​
Common Error Codes

Status CodeDescription
400Invalid request parameters, such as a non-existent model name, invalid message structure, or invalid tool definition
401Missing, invalid, or expired API Key
402Quota insufficient
413Request body too large
429Request rate limit exceeded
500Internal server error
503Upstream unavailable or the system is temporarily overloaded
If an interface page marks a parameter as “optional,” it does not mean that all models support that field. Whether it is ultimately passed through and takes effect still depends on the capabilities of the actual channel it is distributed to.
  1. Text Model Support Matrix
  2. Chat Completions Interface (streaming by default)
  3. OpenAI Multimodal Responses Interface
  4. Claude Messages Interface
  5. Gemini Native Format
  6. Model List
  7. Realtime Interface