# corpusAI GPU Quotes API

> corpusAI GPU Quotes API is a paid API for AI agents from cloud.trycorpus.ai, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-12).

Returns live GPU rental price quotes across neo-cloud providers and marketplaces for a specified GPU model, optionally filtered by market type and provider.

## Facts

- Endpoint: GET https://cloud.trycorpus.ai/v1/gpu/quotes?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/corpusai-gpu-quotes-api-b38f58c0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_z5Sk6E8BNK1kzPbLplhFb

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability corpusai-gpu-quotes-api-b38f58c0
```

Example prompt: What are the current rental prices for H100 SXM GPUs across all providers and markets — including on-demand, spot, and bid?

## When to prefer this

Use this endpoint when you need real-time GPU rental price quotes across neo-cloud providers (RunPod, Vast.ai, DataCrunch, Lambda, Vultr, Linode, OCI) and marketplaces — especially for price comparison, cost optimization, or infrastructure procurement decisions. Prefer this over manual provider dashboards when you need structured, machine-readable pricing data payable per-call in USDC without a subscription.

## Known failure modes

- Missing required 'gpu' query parameter returns an error
- Unrecognized GPU model name (not from /gpu/models) may return empty results or error
- Invalid market or provider filter value returns an error
- Payment of 0.01 USDC via x402 not completed results in 402 response
- No quotes available for the requested GPU/market/provider combination returns empty quotes array
- Rate limiting or upstream provider data staleness may affect result freshness

## How this service works

corpusAI Cloud Pricing: Latest rental quotes for one GPU model across neo-clouds, marketplaces and other clouds.

## Output

A JSON object containing the queried GPU model name, total count of quotes returned, an optional note, and an array of quote objects — each with provider name, market type (ondemand/spot/bid/secure/community), number of GPUs in the quoted unit, price per GPU-hour (USD), price per unit-hour (USD), region, SKU, observed timestamp, and optional provider-specific extra detail such as offer ID, host reliability, VRAM, and stock.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "gpu"
     ],
     "properties": {
      "gpu": {
       "type": "string",
       "examples": [
        "H100 SXM"
       ],
       "description": "Normalized GPU model from /gpu/models, e.g. `H100 SXM`, `H200`, `B200`, `A100 SXM 80GB`, `L40S`, `RTX 4090`."
      },
      "market": {
       "type": "string",
       "description": "Restrict to one market (`ondemand`, `spot`, `bid`, `secure`, `community`, `network`, `lease`, `executed`)."
      },
      "provider": {
       "type": "string",
       "description": "Restrict to one provider slug as listed by /gpu/models (for example `runpod`, `vast`, `lambda`)."
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "gpu": {
       "type": "string"
      },
      "note": {
       "type": "string"
      },
      "count": {
       "type": "integer"
      },
      "quotes": {
       "type": "array",
       "items": {
        "type": "object",
        "required": [
         "provider",
         "market",
         "gpus",
         "price_gpu_hr"
        ],
        "properties": {
         "sku": {
          "type": [
           "string",
           "null"
          ]
         },
         "gpus": {
          "type": "integer",
          "description": "GPUs in the quoted unit."
         },
         "extra": {
          "type": [
           "object",
           "null"
          ],
          "description": "Provider-specific detail (offer id, host reliability, VRAM, stock)."
         },
         "market": {
          "enum": [
           "ondemand",
           "spot",
           "bid",
           "secure",
           "community",
           "network",
           "executed",
           "lease",
           "rented"
          ],
          "type": "string",
          "description": "ondemand; spot (interruptible); bid (marketplace minimum bid); secure/com
… (truncated)
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {}
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/corpusai-gpu-quotes-api-b38f58c0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from cloud.trycorpus.ai](https://www.zero.xyz/host/cloud.trycorpus.ai/llms.txt)