aifree

List models in the free catalog

list_models

Read-only

Every model some live free offer serves (the data behind aifree.dev/model and GET /api/v1/models), most free sources first: slug, family, vendor, context window, tool calling, vision, JSON mode, open weights and how many free sources serve it. Filter by name, family, provider, capability or minimum context; then call get_model for the sources and rate limits.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_models"
  }
}

Input Schema

Name	Required	Description
`page`	No
`limit`	No	Default 50
`query`	No	Substring of the model slug, name or a source model name
`family`	No	Exact family, e.g. "gpt", "llama", "gemini", "embedding"
`vision`	No	true = only models with vision
`provider`	No	Substring of a source provider, offer name or offer slug, e.g. "groq"
`minContextK`	No	Minimum context window in thousands of tokens, e.g. 128
`toolCalling`	No	true = only models with tool calling

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 28, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint=false, so safety is covered; the description adds genuinely new context: result ordering ('most free sources first'), the field set, and the intended drill-down path to get_model. It says nothing about pagination envelope size or rate limits, which keeps it from a 5.

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?

Two sentences, with the what/ordering first and the filter-then-drill-down workflow second. The parenthetical endpoint reference is a bit dense but each clause carries information.

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?

Since there is no output schema, the description correctly enumerates the returned fields and the sort order, and it tells the agent what to do next. Missing is anything about response envelope, paging beyond the limit default, or total counts.

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 88%, so the baseline is already high, yet the description still adds value by grouping the filters semantically (name/family/provider/capability/minimum context) and pairing 'capability' with vision and tool calling. It adds no syntax details beyond the schema.

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

Purpose4/5

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

States a specific verb+resource ('list' models) and scopes it precisely: 'every model some live free offer serves', tying it to the site page and API endpoint. It also enumerates the returned fields. It does not differentiate itself from look-alike siblings such as find_models or list_free_llm_apis, so it falls short of a 5.

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?

Gives clear filtering guidance ('filter by name, family, provider, capability or minimum context') and explicit chaining ('then call get_model for the sources and rate limits'). It lacks any when-not-to-use or comparison against the other model-search tools, so no 5.

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

All aifree tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.