Agents Index

InferIndex

Online

LLM API prices across 100+ providers: cheapest offer, comparisons, history and cost estimates.

Visit publisherConnectJSON

What it can do: 9 tools

  • search_models read-onlyFind the exact id of an LLM tracked by InferIndex from a name or partial name (e.g. 'deepseek', 'qwen3 max', 'claude opus'). Returns matching model ids and names, best match first.
  • cheapest read-onlyCheapest current API offers for one model across direct providers and aggregators, in USD per 1M tokens (input, output, blended 3:1). Stale prices, and flex/batch tiers, are excluded by default. Optional filters (context
  • compare_providers read-onlyCurrent offers for one model, one line per provider and source (direct or via an aggregator), cheapest first (10 by default), with price, quantization, signals and training on prompts when published; the cheapest offer c
  • price_history read-onlyPrice history of one model: every offer tracked by InferIndex (daily or weekly min/max/last price in USD, or raw price changes), plus the official price of the model's lab over time. Give either days, or from/to (YYYY-MM
  • estimate_cost read-onlyEstimated cost of a workload on one model at each provider: cost per request, and per month if requests_per_day is given, taking the provider's tiered pricing and prompt-cache price into account. Offers sorted by estimat
  • provider_ranking read-onlyProviders ranked by how far below or above the market their prices are: each provider's median gap to the market, in percent (score_pct, negative when below the market), where the market of a model is the median blended
  • list_gpus read-onlyGPU types whose rental price InferIndex tracks (H100, A100, L40S…), with the lowest price per GPU per hour in USD for each tier (guaranteed, community, spot) and the number of GPUs of that configuration. Prices are per G
  • gpu_rentals read-onlyRental offers for one GPU type: provider, price in USD per GPU per hour, number of GPUs in the published configuration, billing and region when published. One block per tier (guaranteed, community, spot), each with its o
  • self_host_or_api read-onlyIs it cheaper to host an open-weights model yourself on rented GPUs, or to use the cheapest API offer? Returns a one-sentence verdict (headline) and the numbers behind it: the break-even volume in million tokens per day,

Connect it

Claude Code
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://mcp.inferindex.dev/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "inferindex": {
      "url": "https://mcp.inferindex.dev/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "inferindex": {
      "type": "http",
      "url": "https://mcp.inferindex.dev/mcp"
    }
  }
}

Questions

What does InferIndex do?

LLM API prices across 100+ providers: cheapest offer, comparisons, history and cost estimates. It exposes 9 tools to AI assistants.

What tools does InferIndex provide?

9 tools, including search_models, cheapest, compare_providers, price_history, estimate_cost, provider_ranking, list_gpus, gpu_rentals, self_host_or_api.

How do I connect InferIndex to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://mcp.inferindex.dev/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does InferIndex require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is InferIndex online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes InferIndex?

@InferIndex on GitHub. The official MCP Registry verified that the publisher controls this GitHub account before accepting the listing.

Similar in Agents & Orchestration