Houtini LM
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOUTINI_LM_MODEL | No | Model to pin for calls when the endpoint lists multiple models. | |
| HOUTINI_LM_API_KEY | No | API key for the endpoint, if the endpoint requires one. | |
| HOUTINI_LM_THINKING | No | Thinking mode: auto, off, or on. | auto |
| HOUTINI_LM_SERIALISE | No | Whether to queue calls one at a time. Set to 0 to disable serialisation for OpenAI, a router, or a batching backend like vLLM. | 1 |
| HOUTINI_LM_MIN_TOKENS | No | Minimum output token budget. Values under 4096 are ignored unless set to 0. | 4096 |
| HOUTINI_LM_STRUCTURED | No | Set to 1 to also return a structuredContent block from inference results. | 0 |
| HOUTINI_LM_ENDPOINT_URL | No | URL of the OpenAI-compatible endpoint, such as LM Studio, Ollama, vLLM, SGLang, a LiteLLM router, OpenRouter, OpenAI, DeepSeek, or Groq. | http://localhost:1234 |
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