Skip to main content
Glama

Chat completions (LLM): Llama 4 Scout

ai_chat
Read-only

Send a prompt, get an answer from Meta's Llama 4 Scout (17B active, 16 experts), with an optional system prompt, up to 1,024 output tokens and adjustable temperature. Fast and cheap. Use for drafting, reasoning steps, Q&A and any quick LLM call without an AI provider account; other open models by name at /v1/chat/completions, harder reasoning at ai_chat_large. Example: prompt=Explain HTTP status code 402 in one sentence.. Price $0.002/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "ai_chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolsNoOptional OpenAI tools array as JSON (function calling, up to 32 functions); the answer then carries tool_calls
promptYesUser prompt, up to 8,000 characters. With no input at all the default prompt is "Explain HTTP status code 402 in one sentence."
systemNoOptional system prompt, up to 2,000 characters
messagesNoOptional OpenAI messages array as JSON (system, user, assistant with tool_calls, tool); replaces prompt and system. Together with tools, at most 20,000 characters
maxTokensNoMaximum output tokens, 1-1024 (default 400)
temperatureNo0-1.5 (default 0.6)
tool_choiceNoOptional: auto, none, required, or a JSON object naming one function
response_formatNoOptional OpenAI response_format as JSON: {"type":"json_object"} or a json_schema

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / prompt / description
      Previous value: -"User prompt, up to 8,000 characters"New value: +"User prompt, up to 8,000 characters. With no input at all the default prompt is \"Explain HTTP status code 402 in one sentence.\""
  2. Changed2 schema fields changed
    • changedInput schema / properties / maxTokens / maximum
      Previous value: -9007199254740991New value: +1024
    • changedInput schema / properties / maxTokens / minimum
      Previous value: --9007199254740991New value: +1
  3. Changed4 schema fields changed
    • addedInput schema / properties / messages
      Added value: +{
      +  "description": "Optional OpenAI messages array as JSON (system, user, assistant with tool_calls, tool); replaces prompt and system. Together with tools, at most 20,000 characters",
      +  "type": "string"
      +}
    • addedInput schema / properties / response_format
      Added value: +{
      +  "description": "Optional OpenAI response_format as JSON: {\"type\":\"json_object\"} or a json_schema",
      +  "type": "string"
      +}
    • addedInput schema / properties / tool_choice
      Added value: +{
      +  "description": "Optional: auto, none, required, or a JSON object naming one function",
      +  "type": "string"
      +}
    • addedInput schema / properties / tools
      Added value: +{
      +  "description": "Optional OpenAI tools array as JSON (function calling, up to 32 functions); the answer then carries tool_calls",
      +  "type": "string"
      +}
  4. Added

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing cost per call ($0.002 via x402 USDC or card key), first-25-free, failed calls free, and that repeats are not free because each call is charged — critical given idempotentHint=false. It also restates the read-only/no-side-effect nature already covered by readOnlyHint and destructiveHint=false, which is redundant rather than additive.

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

Conciseness4/5

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

Core capability, intended uses and alternatives are front-loaded in the first two sentences, which is good structure. However, the closing clause re-states the no-side-effect behavior and repeats the example prompt already given in the schema, adding low-value bulk to an otherwise dense paragraph.

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

Completeness4/5

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

For an 8-parameter tool with full schema coverage and no output schema, it covers cost model, model identity, token limits and routing to alternatives. It does not describe the response shape beyond noting that tool_calls appear when tools are supplied, leaving return-format expectations partly implicit.

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

Parameters3/5

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

Schema coverage is 100%, so all eight parameters are already described in the schema; the description mostly echoes the system-prompt, 1,024-token and temperature facts already there. It adds a worked example prompt but no new format or constraint detail beyond the schema, so baseline 3 applies.

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?

Opens with a concrete verb+resource ('Send a prompt, get an answer') and names the exact backend model and its size/architecture. It differentiates from alternatives by naming ai_chat_large for harder reasoning and pointing to /v1/chat/completions for other models by name.

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

Usage Guidelines5/5

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

Explicitly lists intended uses (drafting, reasoning steps, Q&A, quick LLM calls without a provider account) and routes harder reasoning to ai_chat_large and other models to a different endpoint. It also flags the no-account use case as the selecting condition.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.