LMX Cloud LLM Inference

chat_completion

Call LMX Cloud OpenAI-compatible chat completions. Prefers a pre-funded API key (Bearer / api_key); when omitted and x402 is enabled, requires a USDC pay-per-call payment. Optional image_url / images enable vision input (OpenAI content-parts format) — use a vision model such as llama-3.2-90b-vision, qwen-3.6-35b, or qwen-3.5-35b.

Input Schema

TableJSON Schema

Name	Required	Description
`model`	No	Optional model name or alias. Uses default if omitted.
`images`	No	Optional additional images (https URLs or data:image/...;base64,... URIs). Requires a vision-capable model.
`prompt`	Yes	User prompt to send to the selected model.
`api_key`	No	Optional LMX API key (lmx_...). Prefer MCP client Authorization header or env; use this to override per call.
`image_url`	No	Optional image as an https URL or data:image/...;base64,... URI. Requires a vision-capable model.
`max_tokens`	No	Optional max completion tokens.
`temperature`	No	Optional sampling temperature.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed2 schema fields changedJul 18, 2026

addedInput schema / properties / image_url

Added value: +{
+  "description": "Optional image as an https URL or data:image/...;base64,... URI. Requires a vision-capable model.",
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / images

Added value: +{
+  "description": "Optional additional images (https URLs or data:image/...;base64,... URIs). Requires a vision-capable model.",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "type": "array"
+}

First observedJul 16, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries burden. It discloses authentication preferences, payment options, and vision requirements. It does not state non-destructive nature or rate limits, but the information given is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first states core function, second adds critical details on auth and vision. No wasted words, front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 7 parameters, no output schema, and no annotations, the description covers core functionality but lacks explanation of return values or error handling. Could be more complete, especially since no output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so baseline is 3. Description adds extra context: authentication preferences, vision model names, and clarifies that images/url require vision model. Adds value beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Call' and resource 'LMX Cloud OpenAI-compatible chat completions', and distinguishes from sibling tools like get_balance or web_search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides context for when to use (chat completions), mentions authentication options and vision capability, but does not explicitly contrast with alternatives or provide when-not-to-use scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All LMX Cloud LLM Inference tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: chat completion, balance, pricing, status, usage, models, cost estimation, and web search. No two tools perform overlapping functions.

Naming Consistency5/5

All tools follow a consistent snake_case verb_noun pattern (e.g., chat_completion, get_balance, list_models). No mixing of conventions.

Tool Count5/5

8 tools is well-scoped for a cloud LLM inference server, covering core operations (chat, models, pricing, usage, balance, status) plus a web search add-on. Not excessive or too sparse.

Completeness4/5

The tool set covers essential LLM inference and account management workflows. Minor gaps exist (e.g., no streaming parameter docs, no model detail retrieval), but the core surface is complete.

Resources

Need Help?