pics.wick.compute/market

up checked 2026-11-11T07:39:42.630Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

compute.wick.pics

Publisher-provided description

Live GPU spot market: 1,700+ offers, 10 provider feeds. History, watches, limit orders, no fee

Summary by lookupd

Searches live GPU rental offers across providers, compares prices and history, sets watches and limit orders, and places or destroys…

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http market https://compute.wick.pics/mcp/

Codex, remote (streamable-http)

codex mcp add market --url https://compute.wick.pics/mcp/

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "market": {
      "url": "https://compute.wick.pics/mcp/"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (25 tools)

Publisher-provided text

• search_offers Search live GPU offers. gpu matches the model name (e.g. '4090', 'H100'). offer_class: on_demand | interruptible | reserved. country: ISO-2 (e.g. US), a
• get_offer Fetch one offer by its id (from search_offers).
• market_stats Live market snapshot: total offers, GPU models, idle-capacity share, per-provider freshness/health, cheapest price per model, current fee_bps.
• price_history Price history for one GPU model (exact name from search_offers/market_stats, e.g. 'RTX 4090'). offer_class: on_demand | interruptible. Returns per-provider
• idle_history The idle-capacity index over time: share of listed GPU capacity that is interruptible (spot/bid) — idle hardware looking for work. Points are [ts, idle_
• best_value Perf-per-dollar board: for each GPU model, best live price vs its FP16 tensor throughput (dense, vendor spec sheets) -> TFLOPS per dollar-hour. The answ
• provider_reliability How dependable each provider's data feed has been for this station (poll success over the trailing window), plus the provider's own average machine reli
• price_position Rent-now-or-wait context: where the current best price for one GPU model sits inside its own trailing 7/30-day range (percentile, 24h trend, verdict). D
• spot_spread On-demand vs interruptible spread: the live discount for idle capacity per model; pass gpu_model for its history too.
• will_it_fit Will this model fit, and what does a fitting machine cost right now? Deterministic VRAM arithmetic — weights (params x bytes/precision) + KV cache (2 x
• true_cost_notes The billing fine print behind the $/hr, verified per provider from their own published pages (source URL + date on every claim): billing granularity (pe
• register_account Create a metering account: returns a bearer token (shown once, we keep only a hash). Pass it as account_token on rent calls to build a usage ledger you
• account_usage Your metered usage ledger: placements, destroys, estimated hours and USD, and the platform fee (2.5%, $0.01 min, $5.00 cap per lease per UTC day) priced
• create_watch Create a price watch (tripwire): fires when the best live fee-adjusted price per GPU-hour matching gpu (and optional offer_class) drops to or under max_
• watch_status Current state of a watch: armed/tripped, last price seen, recent events, and the best matching offer right now.
• delete_watch Delete a watch by id.
• create_limit_order Place a standing LIMIT ORDER: when the best live fee-adjusted price for gpu (and optional offer_class) trades at or under max_price_per_gpu_hr, the stat
• limit_order_status State of a limit order (armed/ticketed/filled/cancelled/expired), last price seen, recent events. Pass order_secret to also read the live fill ticket wh
• cancel_limit_order Cancel a limit order. Requires the order_secret from create_limit_order.
• rent_x402 Rent a prepaid block of GPU time with a wallet and NO account, NO API key and no human, over x402 (HTTP 402 micropayments, USDC on Base). Call it with
• rent_offer Place a rental on YOUR provider account (BYO key — it is used for this one call and never stored). Default is a DRY RUN returning exactly what would be
• rent_best One-shot rent: search the live book with these filters and place on the best (cheapest) matching offer — 'cheapest H100 under $2/hr, go'. Same guarantee
• rental_status Live state of an instance on your account: running/starting/stopped/ gone, uptime, price, estimated spend so far, and the budget guard's state if one is
• destroy_rental Destroy an instance previously placed on your account (vast or runpod). Your key passes through and is never stored.
• fill_limit_order Execute a limit order's live fill ticket on YOUR provider key (used for this one call, never stored). Only works while the order is ticketed; the offer

Details

• Version: 1.1.1
• Transports: streamable-http
• Uptime (7 days): 75%
• Median latency: 1554 ms
• First indexed: 2026-11-01T10:08:17.436Z
• Last seen in registry: 2026-11-01T10:08:17.455Z
• Repository: https://github.com/aitools420/compute-wick
• Website: https://compute.wick.pics/agents/

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/pics.wick.compute/market.svg)](https://lookupd.com/servers/pics.wick.compute/market)

• 62033 servers
• Last crawl: 2026-11-11T15:38:39.561Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp