Overview — ML Junction docs

ML Junction is a capability-aware LLM gateway. Your application sends one stable request format, and the gateway selects an eligible provider route, enforces capability and privacy requirements, applies retry and fallback policy, records usage, and returns routing and billing evidence.

Use the canonical Responses API when you want the full routing, structured-output, multimodal, context-management, privacy, and receipt surface. Use the OpenAI-compatible Chat Completions and Embeddings endpoints when migrating existing SDK integrations.

Endpoint · Authentication · Purpose
/v1/responses · API key · Canonical text, multimodal, tool, reasoning, and structured-output requests
/openai/v1/chat/completions · API key · OpenAI SDK-compatible Chat Completions
/anthropic/v1/messages · API key · Anthropic SDK-compatible Messages
/v1/embeddings · API key · OpenAI-compatible embedding generation
/v1/routing/preview · API key · Inspect the route plan without calling a model
/v1/models · Public · Model catalog and seven-day popularity statistics
/v1/models/{model}/routes · Public · Provider routes, pricing, capabilities, precision, and telemetry
/v1/models/{model}/usage · Public · Model request and token graph
/v1/providers · Public · Provider directory
/v1/status/{scope} · Public · Provider, model, or route health snapshot
/v1/status/{scope}/{target}/history · Public · Health and latency history
/v1/status/errors · Public · Categorized error graph
/v1/activity/requests/{request_id} · User session · Request plan, attempts, receipt, warnings, and errors

Unknown measured values are omitted instead of returned as zero. Unknown catalog facts with a defined unknown state, such as route precision, use the explicit value "unknown".

Canonical URL: https://mljunction.com/docs/overview