Houtini LM
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOUTINI_LM_MODEL | No | Pin a specific model to use, useful when the server lists many models that all score the same in routing. | |
| HOUTINI_LM_API_KEY | No | API key for the endpoint, if the endpoint requires one. | |
| HOUTINI_LM_THINKING | No | Controls thinking: 'auto' (default, thinking off for models detected as supporting the toggle), 'off' (force off), or 'on' (force on). | |
| HOUTINI_LM_SERIALISE | No | Set to 0 to turn off serialisation (queuing one call at a time). Default is on for a single GPU; OpenRouter skips the queue. | |
| HOUTINI_LM_MIN_TOKENS | No | Set to 0 to allow tiny token caps under 4,096 to be honoured; by default caps under 4,096 are ignored. | |
| 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. | |
| HOUTINI_LM_ENDPOINT_URL | No | URL of the OpenAI-compatible endpoint (LM Studio, Ollama, vLLM, SGLang, LiteLLM router, OpenAI, etc.). Defaults to http://localhost:1234 (LM Studio). |
Instructions
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.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessNo issues