End Point · RTX 5090 GPU 1-Hour Rental
Provision one-hour access to RTX 5090 GPU compute with connection credentials.
What it does
Provision one-hour access to RTX 5090 GPU compute with connection credentials.
- Run short ML inference jobs on high-end GPU
- Execute compute-intensive rendering tasks
- Benchmark algorithms on RTX 5090 architecture
- Access GPU for urgent development and testing
Ideal buyer
ML engineers, researchers, and developers needing on-demand RTX 5090 access without long-term cloud commitments.
Run this through your governed agent wallet.
- 01Bootstrap AXON once with
npx @axon402/init. - 02Use the AXON runtime MCP tools to
search_x402_servicesorinspect_x402_offerfor this service. - 03Quote, test-buy, then run the governed paid fetch through AXON.
Send this
Prompt for your agent
A natural-language instruction for your LLM agent — with this endpoint exposed as a tool — to call this resource. Not sent to the endpoint; the endpoint consumes the JSON body below.
Pasting this prompt into a raw ChatGPT or unconfigured agent will notexecute the paid endpoint flow. Run it through an agent with the AXON runtime / MCP tools exposed (see “Use with AXON” above) so the 402 challenge, quote, and governed fetch are handled for you.
“Rent an RTX 5090 GPU for 1 hour to run a Stable Diffusion batch inference job.”
Endpoint request body
The JSON payload your agent sends to the endpoint.
Advanced HTTP details
For integrators who need the raw protocol surface. Most agents should use AXON above instead of calling these directly.
curl fallback
curl https://end-point-production.up.railway.app/rent-1h \ -H "Content-Type: application/json" \ -H "X-PAYMENT: [signed_payment_envelope]"
Payment & settlement details
Raw on-chain settlement parameters. AXON above handles these automatically through quote / test-buy / governed fetch.
Price & network
Trust & risk
More in Compute
Browse all →Other resources in this category
Category proxy — we don't track live co-purchase signals yet.