INDIVIDUAL MCP TOOL

compare_models

Side-by-side comparison of 2-5 models: specs, benchmarks, pricing, and fit on the given hardware.

llmap.ainone authenticationAvailability not checked

LIVE ENDPOINT

https://llmap.ai/mcp

No auth detected

Connect to this endpoint to inspect the live schema for compare_models and invoke it with your own arguments.

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.llmap]
url = "https://llmap.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "llmap": {
      "type": "http",
      "url": "https://llmap.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: llmap
Remote MCP URL: https://llmap.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "llmap": {
      "url": "https://llmap.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "llmap": {
      "type": "http",
      "url": "https://llmap.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "llmap",
  "transport": "streamable-http",
  "url": "https://llmap.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

check_fit — Check whether a model runs on given hardware: verdict (runs/offloads/wont_fit/hosted), usable context, estimated decode speed.
get_hardware — Full spec sheet for a GPU or Apple Silicon chip by slug.
recommend_hardware — Recommend hardware for a model, budget, and workload, with fit and speed for each pick.
compare_buy_vs_rent — Break-even analysis: buying hardware vs renting hosted inference for a monthly token volume.
get_model — Full model card: specs, quants, license terms, benchmark scores, and where to run it.
search_models — Search/filter the model catalog by name, size, vendor, modality, license, or what fits in a given memory budget.
list_provider_offers — Hosted offers for a model, each carrying its own billingUnit (per_1m_tokens, per_audio_minute or per_1m_characters) — never compare prices across units.
get_provider — Provider profile: models served, pricing, endpoint regions, privacy policies.