Published GPU list rates (no auth)
List rates for every sellable GPU model (community and verified, per GPU-hour) and online token rates for public models, with no API key required. GPU rates are read from the platform's GPU catalog. Unauthenticated, so it never applies a caller's negotiated overrides: GET /v1/pricing answers with those and keeps its API key. Hidden models, and models missing either tier, are omitted rather than quoted at zero. Served from a short-lived cache, so generatedAt trails the request.
Required permission
Requires no authentication.
Published list rates
application/json- response
gpu*array<>model*array<>generatedAt*stringWhen the catalog was last read. Inside the cache window the same body is replayed, so this trails the request that received it.
date-timecurl -X GET 'https://api.openrelay.inc/v1/public/pricing'{ "gpu": [ { "id": "string", "name": "string", "manufacturer": "string", "vramGb": 0, "architecture": "string", "formFactor": "string", "interconnect": "string", "communityCents": 0, "verifiedCents": 0 } ], "model": [ { "id": "string", "inputPerMTokens": 0, "cachedInputPerMTokens": 0, "cacheWritePerMTokens": 0, "outputPerMTokens": 0 } ], "generatedAt": "2019-08-24T14:15:22Z"}GPU + CPU pricing GET
Returns hourly GPU rates per model and tier (with your organization's negotiated rates applied), CPU rates per machine size, and VM disk size bounds.
VM template catalog GET
Returns the VM template catalog: each template's name, slug, OS type and version, driver version, whether it needs a GPU, and which GPU models it supports.