# GPUsMarket (slim)

> GPUsMarket is a peer-to-peer GPU marketplace from Tyga.Cloud Ltd. Agents rent hosts' NVIDIA GPUs and Macs, or on-demand cloud GPUs, as Ollama and OpenAI-compatible endpoints billed per second, through a REST API, CLI and MCP server.

- Full: https://www.anchorterminal.com/tools/gpusmarket.md (~6,750 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/tools/gpusmarket.json · canonical https://www.anchorterminal.com/tools/gpusmarket
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07 · pricing https://www.anchorterminal.com/tools/gpusmarket#pricing · reviews https://www.anchorterminal.com/tools/gpusmarket#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**E · 39.6/100 · rank #1318 of 1486 · #21 in GPU & serverless compute · not agent-ready · confidence low**


Assessment: An agent can sign up with one API call, search priced GPUs without a key, rent a peer or cloud GPU as an Ollama or OpenAI-compatible endpoint and stop it, billed per second. Prompts on peer rentals pass through individuals' machines, the CLI is obfuscated, and there is no status page, security policy or free tier.

## Facts

- Kind: HTTP API · vendor: Tyga.Cloud Ltd · category: GPU & serverless compute · legal entity: Tyga.Cloud Ltd · provenance 63/100
- Endpoint: `https://gpusmarket.com/api/v1` (stdio, SSE (legacy))
- Auth: API key · pricing: Pay per use · x402: no · licence: Proprietary. The gpusmarket CLI and gpusmarket-host packages ship under Tyga.Cloud Ltd licences that allow use only with the platform, as obfuscated JavaScript
- Benchmark probes: not run yet, so Performance is pending
- Live, from our pollers (not part of the score): up at 2026-11-07 18:20 UTC · uptime 30 days 100.0% (200 probes) · p50 157 ms · p95 245 ms over 24 hours
- Surface listed: The REST API under gpusmarket.com/api/v1, the gpusmarket CLI and its stdio MCP server, read from llms.txt, /docs, the home page, terms and privacy policy, the npm packages (read as text, not installed), the jyswee/gpusmarket repository, the MCP registry and Companies House on 6 November 2026. No account was made and nothing was rented
- Which GPUsMarket: gpusmarket.com, a division of Tyga.Cloud Ltd (company 14643275, England and Wales, incorporated 2023). The domain was registered on 24 March 2025
- Rental types: Peer rentals on hosts' own GPUs and Macs, served through Ollama or llama.cpp, and on-demand cloud instances (Ollama, Docker with SSH and Jupyter, or SSH) that the docs say provision in about 30 seconds. Cloud prices include GPUsMarket's margin, and the upstream provider isn't named
- Workloads: LLM chat and embeddings, image generation (SDXL, Flux), Kokoro speech and Whisper transcription, and Wan2.1 video, each on listings of the matching type
- GPU pools: Several rentals behind one OpenAI-compatible endpoint with round-robin, least-loaded, model-match or random routing and failover
- Errors: 400, 401, 429, 502 when a host is offline or its tunnel is down, and 504 after 120 seconds
- Hosts: Anyone with an NVIDIA GPU or Apple Silicon Mac can host with `npx gpusmarket-host` and keep 90% of revenue; listings below 80% uptime over 7 days can be suspended
- Data retention: Account data deleted within 90 days of closure, billing records kept up to 7 years, per the privacy policy (effective March 2026). Stripe and MongoDB are named processors
- Prices: RTX 3060, lowest listed $0.08 per GPU-hour; RTX 4090 $0.35 per GPU-hour; Minimum per rental $0.50 per transaction

- Scores: Reliability 33, Performance pending, Schema & documentation 52, Agent ergonomics 50, Security & auth 30, Payments & pricing 30, Task success pending, Maintenance & community 69, Transparency & trust 50 · negative events -3 · total over the 7 assessed categories
- Why: Reliability, Read with the hosted lines. · Schema & documentation, API and MCP reading. · Agent ergonomics, API and MCP reading. · Security & auth, Account keys are all-powerful within the account, with no scopes, expiry or rotation documented, but each rental gets its own proxy token (1… · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, gpusmarket 2.5.1 on 16 October 2026, 21 days before this check (30). · Transparency & trust, Closed, under Tyga.Cloud licences that are clear on use, but the docs call gpusmarket-host MIT open source while the package says otherwise…
- Sources: 11, open questions: 3, both in the full twin
- Capabilities: compute.gpu, compute.endpoints, compute.containers
- JSON: https://www.anchorterminal.com/api/v1/tools/gpusmarket.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/gpusmarket.svg` or a link to https://www.anchorterminal.com/tools/gpusmarket from a page on gpusmarket.com or one of its subdomains, or the README at the root of github.com/jyswee/gpusmarket, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.
- Support: https://gpusmarket.com/docs; more in the full twin

## Before you call it

1. Don't send confidential data to peer rentals, since requests pass through the host's machine
2. Stop every rental with `POST /api/v1/marketplace/rentals/{id}/stop`, because billing runs per second until it stops
3. Use the per-rental token for inference and keep the `gpu_` account key out of inference clients
4. Treat 502 as host offline and rent another listing rather than retrying the same one
5. Ask the person to add a card before renting, since each rental places a hold on it

## Connect

```bash
npm install -g gpusmarket
```

```bash
curl "https://gpusmarket.com/api/v1/marketplace/search?gpu=RTX%204090&maxPrice=1.00"
```

```bash
claude mcp add gpusmarket -- gpusmarket mcp-serve
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/gpusmarket

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Nebius AI Cloud | BB | 71.2 | compute.gpu, compute.endpoints, compute.containers | https://www.anchorterminal.com/tools/nebius-ai-cloud.min.md |
| Cloud Run GPUs | B | 68.4 | compute.gpu, compute.endpoints, compute.containers | https://www.anchorterminal.com/tools/cloud-run-gpus.min.md |
| Hugging Face Inference Endpoints | B | 66.7 | compute.gpu, compute.endpoints, compute.containers | https://www.anchorterminal.com/tools/hugging-face-inference-endpoints.min.md |
| Replicate Deployments | B | 65.2 | compute.gpu, compute.endpoints, compute.containers | https://www.anchorterminal.com/tools/replicate-deploy.min.md |
| Baseten | B | 62.7 | compute.gpu, compute.endpoints, compute.containers | https://www.anchorterminal.com/tools/baseten.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)