Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OMLX_MODELNoFallback key for VISION_MODEL: Vision model ID or alias.
OMLX_API_KEYNoFallback key for VISION_API_KEY: Bearer token for authorization.
OPENAI_MODELNoFallback key for VISION_MODEL: Vision model ID or alias.
VISION_MODELNoVision model ID or alias. If omitted and the endpoint hosts a single model, auto-selects that model. Fallback keys: OPENAI_MODEL, OMLX_MODEL.Q-Vision
OMLX_BASE_URLNoFallback key for VISION_BASE_URL: Base URL of the oMLX/OpenAI-compatible vision server.
OPENAI_API_KEYNoFallback key for VISION_API_KEY: Bearer token for authorization.
VISION_API_KEYNoBearer token for authorization. Fallback keys: OPENAI_API_KEY, OMLX_API_KEY.omlx
OPENAI_BASE_URLNoFallback key for VISION_BASE_URL: Base URL of the OpenAI-compatible vision server.
VISION_BASE_URLNoBase URL of the OpenAI-compatible vision server. Fallback keys: OPENAI_BASE_URL, OMLX_BASE_URL.http://localhost:8000/v1
OMLX_MAX_IMAGE_SIDENoMaximum pixel length of the longest rendered page edge (snapped down to a multiple of 28).1792
OMLX_MAX_CONCURRENCYNoMaximum concurrent 3-page Page Windows processed in multi-window PDFs.1

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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources