Generate a chat completion using an OpenRouter model

Generate a chat completion using a predefined model preset (smart, cheap, creative, fast, coder)

Analyze a task and recommend the best model preset (smart, cheap, creative, fast, coder)

Refine and optimize a draft prompt using best practices for LLMs

Generate a consensus completion by querying multiple distinct models in parallel and synthesizing their responses using a synthesizer model.

Execute a chat completion with intelligent, automatic cost-aware model routing based on prompt size, required context length, and task attributes.

List available models on OpenRouter

Filter and search available OpenRouter models based on requirements (e.g. cost, context window, vision)

Get the total token usage and estimated cost for the current session

Check your OpenRouter credit balance

Get information about the current API key (limits, usage, etc.)

Set a session-wide spending limit (in USD) and warning threshold

Check the current session spending and budget status

Analyze an image (local file or URL) using a vision-capable model

Scan a project directory to index symbols (functions, classes, variables) for cross-project awareness

Search for symbols across all indexed projects

Perform deep semantic indexing of a project (code chunking + embeddings) for code search

Search for code logic across indexed projects using natural language

Store text with optional tags and project association for semantic retrieval

Search for semantically similar information in memory

Delete entries from semantic memory by tag or project

Analyze log snippets from multiple systems to find root causes and correlations

Analyze shared dependencies and semver conflicts across multiple projects

Perform diagnostic checks on OpenRouter credentials, files, and server environment