Discover/Ornn API
live

Ornn APIdata.ornn.com

Get current per-GPU-hour index prices for H100 SXM, H200, A100 SXM4, B200, and RTX 5090 from data.ornn.com. Live market data via one endpoint.

This API takes change requests — .
Endpoint health
verified 4h ago
get_h100_index
1/1 passing latest checkself-healing
Endpoints
1
Updated
5h ago

What is the Ornn API?

The data.ornn.com API exposes one endpoint, get_h100_index, that returns current index prices for five tracked GPU types — H100 SXM, H200, A100 SXM4, B200, and RTX 5090. Each response includes an ISO 8601 timestamp of the latest index update and an array of GPU pricing entries with the GPU name, index price per GPU-hour in USD, and the pricing unit. No input parameters are required.

This call costs1 credit / call— charged only on success
Try it

No input parameters required.

api.parse.bot/scraper/e0a4db76-d369-4df7-9055-acfd92eb17df/<endpoint>
Ready to send
Fill in the parameters and hit sign in to send to see live response data here.
Call it over HTTPgrab a free API key at signup
curl -X GET 'https://api.parse.bot/scraper/e0a4db76-d369-4df7-9055-acfd92eb17df/get_h100_index' \
  -H 'X-API-Key: $PARSE_API_KEY'
Python SDK · recommended

Typed, relational, agent-ready

A generated client with real types, enums, and the links between objects — the structure a flat JSON response can't carry. Autocompletes in your editor and reads cleanly to coding agents.

  • Fully typed · autocompletes
  • Objects link to objects
  • Typed errors & pagination

Typed Python client. Set up the SDK in your uv project, then pull this API’s typed client:

uv add parse-sdk
uv run parse init
uv run parse add --marketplace data-ornn-com-api

uv run parse add --marketplace pulls a pinned snapshot of this canonical API — it won’t change underneath you. To customize it, subscribe and swap to your own copy.

"""Walkthrough: Ornn GPU Index API — fetch current GPU compute pricing."""
from parse_apis.data_ornn_com_api import Ornn, UpstreamError

client = Ornn()

# Fetch the latest GPU compute index prices
try:
    index = client.gpu_index.get()
except UpstreamError as e:
    print(f"Upstream unavailable: {e}")
    raise
print(f"Index date: {index.date.isoformat()}")

# Display per-GPU pricing
for price in index.gpus:
    print(f"  {price.gpu}: ${price.index_price_per_hour:.4f} {price.unit}")

print("exercised: gpu_index.get")
All endpoints · 1 totalmissing one? ·

Returns the latest daily GPU compute index prices for all tracked GPU types (H100 SXM, H200, A100 SXM4, B200, RTX 5090). Each entry includes the GPU name, the index price per GPU-hour in USD, and the unit. The date field indicates the timestamp of the most recent index update. Single request, no pagination.

Input

No input parameters required.

Response
{
  "type": "object",
  "fields": {
    "date": "ISO 8601 timestamp of the latest index update",
    "gpus": "array of GPU pricing entries, each with gpu name, index_price_per_hour, and unit"
  },
  "sample": {
    "data": {
      "date": "2026-08-08T20:00:00.000Z",
      "gpus": [
        {
          "gpu": "A100 SXM4",
          "unit": "USD/GPU-hr",
          "index_price_per_hour": 1.04625
        },
        {
          "gpu": "B200",
          "unit": "USD/GPU-hr",
          "index_price_per_hour": 5.72625
        },
        {
          "gpu": "H100 SXM",
          "unit": "USD/GPU-hr",
          "index_price_per_hour": 2.65625
        },
        {
          "gpu": "H200",
          "unit": "USD/GPU-hr",
          "index_price_per_hour": 4.555
        },
        {
          "gpu": "RTX 5090",
          "unit": "USD/GPU-hr",
          "index_price_per_hour": 0.48791666666666667
        }
      ]
    },
    "status": "success"
  }
}

About the Ornn API

What the API Returns

The get_h100_index endpoint returns a single JSON object containing two top-level fields: date and gpus. The date field is an ISO 8601 timestamp indicating when the index was last updated. The gpus field is an array where each entry carries three fields: gpu (the GPU model name), index_price_per_hour (a numeric USD value), and unit (the billing unit, typically per GPU-hour).

GPU Coverage

The endpoint currently tracks five GPU types: H100 SXM, H200, A100 SXM4, B200, and RTX 5090. These represent a cross-section of high-end data center and prosumer GPU models commonly traded in cloud compute markets. All five entries are returned in every response — there is no filtering by GPU type on the request side.

Freshness and Data Shape

The date timestamp in the response reflects the most recent index update published by data.ornn.com. Because the endpoint takes no parameters, callers poll it to detect price changes over time. Building a time-series store requires the caller to record successive responses and compare date values. The API itself does not expose historical data or trend fields.

Reliability & maintenanceVerified

The Ornn API is a managed, monitored endpoint for data.ornn.com — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when data.ornn.com changes and a check fails, the API is automatically queued for repair and re-verified. It is built to keep working as the site underneath it changes.

This isn't an official data.ornn.com API — it's an independent, maintained REST wrapper over public data. Where the source has no official API (or only a limited one), Parse gives you a stable contract over a source that never promised one, and keeps it current. Need a new endpoint or field? You can revise it yourself in plain English and the agent rebuilds it against the live site in minutes — contributing the change back to the shared API is free.

Last verified
4h ago
Latest check
1/1 endpoint passing
Maintenance
Monitored & self-healing
Will this API break when the source site changes?+
It's built not to. Every endpoint is health-checked on a schedule with automated test probes. When the source site changes and a check fails, the API is automatically queued for repair and re-verified — that's the self-healing layer. Each API page shows when its endpoints were last verified. And because marketplace APIs are shared, any fix reaches everyone using it.
Is this an official API from the source site?+
No — Parse APIs are independent, managed REST wrappers over publicly available data. That is the point: where a site has no official API (or only a limited one), Parse gives you a maintained, monitored endpoint for that data and keeps it working as the site changes — so you get a stable contract over a source that never promised one.
Can I fix or extend this API myself if I need a new endpoint or field?+
Yes — and you don't have to wait on us. This API was generated by the Parse agent, which stays attached. Describe the change in plain English ("add an endpoint that returns reviews", "fix the price field") in the revise box on the API page or via the revise_api MCP tool, and the agent rebuilds it against the live site in minutes. Contributing the change back to the public API is free.
What happens if I call an endpoint that has an issue?+
Errors are machine-readable: a bad call returns a clean status with the list of available endpoints and a repair hint, so an agent (or you) can recover or trigger a fix instead of failing silently. Confirmed failures feed the automatic repair queue.
Common use cases
  • Alerting when H100 SXM or H200 index prices cross a cost threshold for GPU budget management
  • Comparing per-GPU-hour costs across H100 SXM, A100 SXM4, and B200 before placing cloud compute orders
  • Feeding current GPU index prices into internal dashboards for infrastructure cost tracking
  • Building a lightweight time-series log of GPU price movements by polling get_h100_index on a schedule
  • Informing procurement decisions for RTX 5090 vs. data center GPU rentals using live index data
  • Populating a GPU cost calculator with real-time index_price_per_hour values for workload estimation
Pricing & limitsSee full pricing →
TierPriceCredits/monthRate limit
Free$0/mo2005 req/min
Hobby$30/mo1,00020 req/min
Developer$100/mo5,000100 req/min
Team$300/mo20,000300 req/min
Company$1,000/mo100,000500 req/min

Each endpoint has a fixed posted price per successful call — most fall between 1 and 10 credits — shown on this API's page before you run it. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.

Frequently asked questions
Does data.ornn.com have an official developer API?+
data.ornn.com does not appear to publish a documented public developer API. This Parse API provides structured access to the GPU index data shown on their preview page.
What exactly does `get_h100_index` return for each GPU?+
Each entry in the gpus array contains three fields: the GPU model name (e.g. 'H100 SXM'), the index_price_per_hour as a numeric USD value, and unit indicating the billing granularity. The top-level date field gives the ISO 8601 timestamp of the index update that produced those prices.
Can I retrieve historical GPU price data or filter results by GPU type?+
Not currently. The endpoint returns the latest index snapshot for all five tracked GPUs in a single response; it does not accept filter parameters and does not expose historical pricing records. You can fork this API on Parse and revise it to add a historical data endpoint if data.ornn.com surfaces that data elsewhere.
Are GPUs beyond the five currently tracked — such as L40S or H100 PCIe — covered?+
Not currently. The API covers H100 SXM, H200, A100 SXM4, B200, and RTX 5090. You can fork it on Parse and revise to add additional GPU entries if data.ornn.com begins tracking other models.
How stale can the returned prices be?+
The date field in each response tells you exactly when the index was last updated on data.ornn.com's side. The API reflects the most recently published index at the time of your request. There is no guaranteed update cadence specified; inspecting the date value is the reliable way to assess freshness.
Page content last updated . Spec covers 1 endpoint from data.ornn.com.
Related APIs in FinanceSee all →