AI

OpenRouter

OpenRouter is one API in front of many model vendors: a single key, an OpenAI-compatible chat endpoint, and models addressed as provider/model — openai/gpt-4o, anthropic/claude-3.5-sonnet.

Authentication

  • API key

Actions

Generic API request. Call any OpenRouter API endpoint on this connection, for the case where no shipped action covers it yet. The connection supplies the base URL, the authentication and the egress route, so only the path, query and body are yours to fill.

  • Chat CompletionsRoute a chat completion through OpenRouter (OpenAI-compatible POST /chat/completions) with optional model fallbacks and provider routing.
  • Chat Completions (Streaming)Chat Completions (Streaming) for openrouter (OpenAI-compatible) via connection context.
  • EmbeddingsEmbed text through OpenRouter (OpenAI-compatible POST /embeddings), with optional provider routing.
  • Get API key infoRetrieve metadata about the API key used to authenticate (label, usage, limit) (GET /key).
  • Get creditsRetrieve total credits purchased and used for the authenticated account (GET /credits).
  • Get generationRetrieve stats and metadata for a completed generation by id (GET /generation?id=...).
  • List modelsList the models available through OpenRouter (GET /models).
  • Typed decision (System One)Ask a decision model typed questions about a piece of state and get calibrated probabilities back (POST /systemone, TypeSafe's Jev models).

Triggers

  • New modelStarts when OpenRouter adds a new model to its catalog, detected by polling GET models and comparing each model's created timestamp against the last-seen value.

Product names, logos and brands are the property of their respective owners and are used here for identification only. Their use does not imply endorsement by, or affiliation with, those owners.