Full Flow Agentic — A single Anthropic Messages gateway that runs the server-owned web-search loop through Praxis core’s iterative_request_router (IRR) and serves BOTH streaming and buffered clients from one pipeline. anthropic_web_search selects the transport per request from the client’s stream flag (terminal_streaming: true)
Messages Native Vllm — Routes native Anthropic Messages API traffic (/v1/messages and /v1/messages/count_tokens) to a vLLM backend that natively serves the Anthropic Messages API, WITHOUT any request or response body translation
Messages Protocol — Routes Anthropic Messages API requests to a native /v1/messages backend
Messages To Openai Vllm — Translates native Anthropic Messages API traffic into OpenAI Chat Completions for a vLLM backend that serves /v1/chat/completions, with the same three-boundary credential isolation as the native passthrough config
Messages To Openai — Transforms Anthropic Messages API requests and responses for Chat Completions-compatible inference backends
Unified Gateway — Routes traffic by classifier-promoted headers so a single listener handles Anthropic Messages, OpenAI Chat Completions, and OpenAI Responses requests
A single Anthropic Messages gateway that runs the server-owned web-search loop through Praxis core’s iterative_request_router (IRR) and serves BOTH streaming and buffered clients from one pipeline. anthropic_web_search selects the transport per request from the client’s stream flag (terminal_streaming: true)
Routes native Anthropic Messages API traffic (/v1/messages and /v1/messages/count_tokens) to a vLLM backend that natively serves the Anthropic Messages API, WITHOUT any request or response body translation
Translates native Anthropic Messages API traffic into OpenAI Chat Completions for a vLLM backend that serves /v1/chat/completions, with the same three-boundary credential isolation as the native passthrough config