Skip to content

data(readiness): list two GPU compute services - #388

Merged
sourcey[bot] merged 1 commit into
mainfrom
data/readiness-compute
Oct 13, 2026
Merged

sourcey[bot] merged 1 commit into
mainfrom
data/readiness-compute

Conversation

@auscaster

Copy link
Copy Markdown
Member

Two listings for the job compute-instance-create (Create a compute instance), from agent readiness R2's cohort:

  • Runpod Pods: POST https://rest.runpod.io/v1/pods, in Runpod's REST OpenAPI document, and the hosted MCP server https://mcp.getrunpod.io/ with its create-pod tool (named in Runpod's own MCP server source). Prepaid credits with auto-pay from a card, so the billing page is the checkout.
  • Vast.ai GPU Instances: PUT https://console.vast.ai/api/v0/asks/{id}/ (create instance), in Vast.ai's OpenAPI document. Agents use its CLI skill rather than an MCP server. Prepaid credits with autobilling by credit card, so the billing page is the checkout.

Every field is bound to the vendor's own public page.

Runpod and Vast.ai, each on the job its product is for: create a compute instance. Each was read from the vendor's own pages: the API that creates a pod or instance, its OpenAPI document, how it authenticates, and how it is paid. Both are prepaid with automatic reloads from a saved card, so each names its billing page as its checkout. Runpod also names its hosted MCP server's create-pod tool.

Signed-off-by: Kam <oss@0state.com>
@sourcey
sourcey Bot merged commit adb12d9 into main Oct 13, 2026
4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant