Connect InferIndex and your agent gets 9 tools, among them cheapest, compare_providers, estimate_cost. It answers at https://mcp.inferindex.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 23 September 2026; the last check, on 6 November 2026, succeeded.
LLM API prices across 70+ providers: cheapest offer, comparisons, history and cost estimates.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
cheapest | Cheapest 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, tools, JSON, visio Inputs: model, min_context, tools, json, vision, region |
compare_providers | Current 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 comes in detail. Pass Inputs: model, sort, limit, detail, region, no_training |
estimate_cost | Estimated 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 estimated cost, cheapest fi Inputs: model, prompt_tokens, output_tokens, cached_ratio, requests_per_day, limit |
gpu_rentals | Rental 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 own cheapest offer, a Inputs: gpu, tier, gpu_count, region, detail |
list_gpus | GPU 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 GPU per hour, as publ |
price_history | Price 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-DD), or at (a date) Inputs: model, days, from, to, at, granularity |
provider_ranking | Providers 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 3:1 price of its pro |
search_models | Find 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. Inputs: query |
self_host_or_api | Is 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, the throughput the Inputs: model, tokens_per_day, requests_per_day, prompt_tokens, output_tokens, utilization |
Every block below points at https://mcp.inferindex.dev/mcp. Pick your client and copy.
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp
{
"mcpServers": {
"inferindex": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.inferindex.dev/mcp"]
}
}
}{
"mcpServers": {
"inferindex": {
"url": "https://mcp.inferindex.dev/mcp"
}
}
}{
"servers": {
"inferindex": {
"type": "http",
"url": "https://mcp.inferindex.dev/mcp"
}
}
}{
"context_servers": {
"inferindex": {
"url": "https://mcp.inferindex.dev/mcp"
}
}
}{
"mcpServers": {
"inferindex": {
"serverUrl": "https://mcp.inferindex.dev/mcp"
}
}
}{
"mcpServers": {
"inferindex": {
"url": "https://mcp.inferindex.dev/mcp"
}
}
}name: InferIndex
version: 0.0.1
schema: v1
mcpServers:
- name: InferIndex
type: streamable-http
url: https://mcp.inferindex.dev/mcp{
"mcpServers": {
"inferindex": {
"httpUrl": "https://mcp.inferindex.dev/mcp"
}
}
}{
"mcpServers": {
"inferindex": {
"type": "http",
"url": "https://mcp.inferindex.dev/mcp"
}
}
}{
"mcpServers": {
"inferindex": {
"url": "https://mcp.inferindex.dev/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.inferindex.dev%2Fmcp&type=streamable_http&id=inferindex&name=InferIndex
It answered our last check on 6 November 2026 in 443 ms. Over 4 checks since 23 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
9, as returned by the server's own tools/list on 9 November 2026: cheapest, compare_providers, estimate_cost, gpu_rentals, list_gpus, price_history, provider_ranking, search_models, and 1 more.
It answered our last check on 6 November 2026 in 443 ms. Over 4 checks since 23 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.inferindex.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.inferindex. Endpoint host: mcp.inferindex.dev. ARD identifier: urn:air:io.github.inferindex:mcp:inferindex.
First indexed 18 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.