Schema | Houtini LM

Houtini LM

Describes the environment variables required to run the server.

Name	Required	Description	Default
`HOUTINI_LM_MODEL`	No	Pin a specific model to use. Without it, houtini-lm scores each available model against the task type and picks the best.
`HOUTINI_LM_API_KEY`	No	API key for the endpoint, if it requires one (e.g. OpenAI, OpenRouter, DeepSeek, Groq).
`HOUTINI_LM_THINKING`	No	Controls thinking/reasoning for models that support it: auto (default, thinking off for detected models), off (force off everywhere), or on (force on, e.g. for bug-hunting).	auto
`HOUTINI_LM_SERIALISE`	No	Set to 0 to turn off the default serialised (one-at-a-time) call queue. Worth doing for OpenAI, a LiteLLM router, or a batching backend like vLLM.	1
`HOUTINI_LM_MIN_TOKENS`	No	Minimum output-token floor for calls. Set to 0 to disable the default floor of 4,096 tokens.	4096
`HOUTINI_LM_STRUCTURED`	No	Set to 1 to include a structuredContent block (answer, model, tokens, timing, quality flags) in each inference result. Leave off for Claude Code, which shows the model only that block when present.	0
`HOUTINI_LM_ENDPOINT_URL`	No	The URL of the OpenAI-compatible endpoint to delegate to (LM Studio, Ollama, vLLM, SGLang, a LiteLLM router, OpenAI, OpenRouter, etc.). Defaults to LM Studio on http://localhost:1234.	http://localhost:1234

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityActive

ResponsivenessNo issues