GetDeploying API

Stop wrestling with fragmented pricing models. Our API aggregates and normalizes GPU market data from 64 cloud providers into a unified, queryable schema. We provide the market intelligence you need to:

Benchmark costs across major hyperscalers and specialized GPU clouds
Programmatically filter by GPU model, VRAM, provider, billing type, and price range
Track pricing trends with data updated approximately once per day
Deploy cost-aware infrastructure using structured, standardized datasets

Authentication

Getting an API Key

To access the API, you'll need an active subscription. You can obtain one here.

Using Your API Key

Authenticate by including your API key in the Authorization header as a Bearer token:

curl -H "Authorization: Bearer YOUR_API_KEY" \
  "https://getdeploying.com/api/gpu-offerings"

List GPU Offerings

Request

GET /api/gpu-offerings

Returns a paginated list of GPU offerings from cloud providers, with detailed specifications and pricing information.

Query Parameters

Parameter	Type	Description	Example
`gpu_model`	string	Filter by GPU slug(s), comma-separated. See Supported GPU Models for all valid slugs	`nvidia-h100` or `nvidia-h100,nvidia-a100`
`provider`	string	Filter by provider slug(s), comma-separated. See Supported Providers for all valid slugs	`aws` or `aws,microsoft-azure,google-cloud`
`provider_country`	string	Filter by provider headquarters country code(s), comma-separated. Use `EU` for all European countries	`US` or `DE,FR` or `EU`
`billing_type`	string	Filter by billing type	`ON_DEMAND`, `RESERVATION`, `SPOT`, `CUSTOM`
`availability`	string	Filter by availability status	`AVAILABLE`, `WAITLIST`, `UNAVAILABLE`, `UNKNOWN`
`interconnect`	string	Filter by GPU interconnect type	`SXM`, `PCIe`, `NVL`
`max_price`	decimal	Maximum total price per hour in USD	`50.00`
`min_gpu_count`	integer	Minimum number of GPUs per instance	`4`
`min_vram`	integer	Minimum VRAM per GPU (GB)	`40`
`min_vram_total`	integer	Minimum total VRAM across all GPUs (GB)	`320`
`min_bandwidth`	integer	Minimum GPU memory bandwidth (GB/s)	`1000`
`min_disk`	integer	Minimum disk storage (GB)	`500`
`sort`	string	Sort order (default: `price_per_gpu_hour`)	`price_hour`, `-price_hour`, `price_per_gpu_hour`, `-price_per_gpu_hour`, `gpu_count`, `-gpu_count`
`page`	integer	Page number for paginated results (default: `1`)	`2`
`page_size`	integer	Items per page (default: `10`, max: `100`)	`25`

Response Format

The API returns paginated JSON with an array of GPU offerings:

{
  "page": 1,
  "page_size": 10,
  "page_count": 4,
  "total": 38,
  "data": [
    {
      "id": "aws-a1b2c3d4e5f6a7b8",
      "external_id": "p5.48xlarge",
      "provider": {
        "id": "aws",
        "name": "Amazon Web Services",
        "website": "https://aws.amazon.com/",
        "country": "US"
      },
      "configuration": {
        "gpu_model": "nvidia-h100",
        "gpu_count": 8,
        "vram_per_gpu_gb": 80,
        "vram_total_gb": 640,
        "gpu_mem_bandwidth_gbps": 3350,
        "supported_precisions": ["FP8", "FP16", "BF16", "TF32", "FP32", "FP64", "INT8"],
        "interconnect_bandwidth_gbps": 900,
        "interconnect": "SXM",
        "cpu_cores": 192,
        "system_ram_gb": 2048,
        "disk_storage_gb": null
      },
      "pricing": {
        "currency": "USD",
        "billing_type": "ON_DEMAND",
        "hourly": 98.32,
        "hourly_per_gpu": 12.29,
        "monthly": 70790.4,
        "note": "On-demand pricing"
      },
      "status": {
        "availability": "AVAILABLE",
        "note": "Instance available at time of verification.",
        "last_verified": "2026-01-15T12:00:00Z"
      }
    }
  ]
}

Field Descriptions

Top-level fields:

Field	Type	Description
`id`	string	Stable unique identifier for this offering
`external_id`	string	Provider's own instance name or ID (eg., "p5.48xlarge"); may be empty

Provider (provider):

Field	Type	Description
`id`	string	Provider slug (eg., "aws", "microsoft-azure")
`name`	string	Provider display name
`website`	string	Provider's website URL
`country`	string \| null	Provider HQ country code (ISO 3166-1 alpha-2)

Configuration (configuration):

Field	Type	Description
`gpu_model`	string	GPU model slug (eg., "nvidia-h100", "nvidia-a100")
`gpu_count`	integer	Number of GPUs in this instance
`vram_per_gpu_gb`	integer \| null	VRAM per GPU in gigabytes
`vram_total_gb`	integer \| null	Total VRAM across all GPUs in gigabytes
`gpu_mem_bandwidth_gbps`	integer \| null	GPU memory bandwidth in GB/s
`supported_precisions`	array \| null	Supported precision formats (eg., ["FP8", "FP16", "BF16", "FP32"])
`interconnect_bandwidth_gbps`	integer \| null	High-speed GPU interconnect bandwidth in GB/s (NVLink or Infinity Fabric). Null means PCIe-only
`interconnect`	string \| null	GPU interconnect/form-factor when a provider offers multiple variants of the same GPU (eg., "SXM", "PCIe", "NVL")
`cpu_cores`	integer \| null	Total CPU cores
`system_ram_gb`	integer \| null	System RAM in gigabytes
`disk_storage_gb`	integer \| null	Disk storage in gigabytes

Pricing (pricing):

Field	Type	Description
`currency`	string	Always `"USD"` — prices are normalized from the original currency
`billing_type`	string	`ON_DEMAND`, `RESERVATION`, `SPOT`, or `CUSTOM`
`hourly`	number \| null	Hourly price in USD
`hourly_per_gpu`	number \| null	Per-GPU hourly price in USD — useful for comparing multi-GPU instances
`monthly`	number \| null	Estimated monthly price in USD (720 hours)
`note`	string	Provider's billing terms summary

Status (status):

Field	Type	Description
`availability`	string	`AVAILABLE`, `UNAVAILABLE`, `WAITLIST`, or `UNKNOWN`
`note`	string \| null	Additional information about availability status
`last_verified`	string \| null	When this offering was last confirmed live by our scrapers (ISO 8601)

Pagination:

Field	Type	Description
`page`	integer	Current page number
`page_size`	integer	Number of items per page
`page_count`	integer	Total number of pages
`total`	integer	Total number of matching items
`data`	array	Array of GPU offering objects

Examples

# Get all H100 offerings
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-offerings?gpu_model=nvidia-h100"

# Filter by provider and billing type
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-offerings?provider=aws&billing_type=ON_DEMAND"

# Query multiple GPU models and providers
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-offerings?gpu_model=nvidia-h100,nvidia-a100&provider=aws,microsoft-azure"

# Find cheapest H100 offerings under $30/hour, sorted by price per GPU
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-offerings?gpu_model=nvidia-h100&max_price=30&sort=price_per_gpu_hour"

# Get large H100 instances (8+ GPUs) sorted by total price
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-offerings?gpu_model=nvidia-h100&min_gpu_count=8&sort=price_hour"

# Sort by descending GPU count (largest instances first)
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-offerings?gpu_model=nvidia-h100&sort=-gpu_count"

# Get all A100 offerings from European providers
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-offerings?gpu_model=nvidia-a100&provider_country=EU"

# Filter by minimum VRAM per GPU
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-offerings?min_vram=80&sort=price_per_gpu_hour"

List GPU Price History

GET /api/gpu-price-history

Returns weekly pricing snapshots for GPU models. By default, returns aggregate statistics across all providers. Use the provider parameter to get price history for a specific cloud provider.

Query Parameters

Parameter	Type	Description	Example
`gpu_model`	string	Filter by GPU model slug. Omit to get snapshots for all models. See Supported GPU Models for all valid slugs	`nvidia-h100`
`provider`	string	Filter by provider slug. When set, returns per-provider snapshots instead of market-wide aggregates. See Supported Providers for all valid slugs	`aws`, `runpod`, `lambda`
`billing_type`	string	Filter by billing type	`ON_DEMAND`, `RESERVATION`, `SPOT`, `CUSTOM`
`date_start`	date	Only include snapshots on or after this date (ISO 8601)	`2026-01-01`
`date_end`	date	Only include snapshots on or before this date (ISO 8601)	`2026-03-01`
`page`	integer	Page number for paginated results (default: `1`)	`2`
`page_size`	integer	Items per page (default: `10`, max: `100`)	`50`

Response Format

{
  "page": 1,
  "page_size": 10,
  "page_count": 3,
  "total": 24,
  "data": [
    {
      "date": "2026-01-06",
      "gpu_model": "nvidia-h100",
      "provider": null,
      "billing_type": "ON_DEMAND",
      "reservation_months": null,
      "currency": "USD",
      "min_price": "1.79",
      "max_price": "12.29",
      "avg_price": "5.44",
      "median_price": "4.76",
      "offering_count": 42,
      "provider_count": 18
    }
  ]
}

Field Descriptions

Field	Type	Description
`date`	string	Snapshot date (ISO 8601)
`gpu_model`	string	GPU model slug (eg., `"nvidia-h100"`)
`provider`	string \| null	Provider slug when filtering by provider, `null` for market-wide aggregates
`billing_type`	string	`ON_DEMAND`, `RESERVATION`, `SPOT`, or `CUSTOM`
`reservation_months`	integer \| null	Commitment length in months (only for `RESERVATION`)
`currency`	string	Always `"USD"`
`min_price`	string	Lowest per-GPU hourly price (across all providers, or for the specified provider)
`max_price`	string	Highest per-GPU hourly price
`avg_price`	string	Average per-GPU hourly price
`median_price`	string	Median per-GPU hourly price
`offering_count`	integer	Number of offerings included in the snapshot
`provider_count`	integer	Number of distinct providers included (always 1 when filtering by provider)

Examples

# Market-wide H100 on-demand price history (aggregated across all providers)
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-price-history?gpu_model=nvidia-h100&billing_type=ON_DEMAND"

# Same query, but scoped to a single provider
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-price-history?provider=runpod&gpu_model=nvidia-h100&billing_type=ON_DEMAND"

# Compare two providers' H100 pricing (make two calls)
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-price-history?provider=aws&gpu_model=nvidia-h100"
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-price-history?provider=runpod&gpu_model=nvidia-h100"

# A100 spot price history
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-price-history?gpu_model=nvidia-a100&billing_type=SPOT"

# Filter by date range
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-price-history?gpu_model=nvidia-h100&billing_type=ON_DEMAND&date_start=2026-01-01&date_end=2026-03-31"

# Paginate through a large result set (update page param as needed)
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-price-history?provider=aws&page_size=100&page=1"

List GPU Models

GET /api/gpus

Returns all GPU models tracked in the database. Useful for discovering valid gpu_model slugs to use as filters.

[
  {
    "id": "nvidia-h100",
    "name": "Nvidia H100",
    "vendor": "NVIDIA",
    "vram_gb": 80,
    "mem_bandwidth_gbps": 3350,
    "precision_formats": ["FP8", "FP16", "BF16", "TF32", "FP32", "FP64", "INT8"],
    "interconnect_bandwidth_gbps": 900
  }
]

List Providers

GET /api/providers

Returns all active cloud providers. Useful for discovering valid provider slugs to use as filters.

[
  {
    "id": "aws",
    "name": "Amazon Web Services",
    "website": "https://aws.amazon.com/",
    "country": "US"
  }
]

Rate Limits

The API includes rate limit information in response headers. For example:

X-RateLimit-Limit: 1000
X-RateLimit-Remaining: 847
X-RateLimit-Reset: 43200

Here's what each header indicates:

X-RateLimit-Limit: Maximum requests allowed per period
X-RateLimit-Remaining: Requests remaining in current period
X-RateLimit-Reset: Seconds until the rate limit resets

Rate Limit Exceeded

When you exceed your rate limit, you'll receive a 429 Too Many Requests response:

{
  "error": "Rate limit exceeded. Try again in 43200 seconds."
}

Error Codes

Status Code	Meaning	Description
`200`	Success	Request completed successfully
`401`	Unauthorized	Invalid or missing API key
`403`	Forbidden	API key is inactive or lacks required permissions
`429`	Too Many Requests	Rate limit exceeded
`500`	Internal Server Error	Something went wrong on our end

Error Response Format

Error responses include a JSON object with an error field:

{
  "error": "Invalid token"
}

Best Practices

Caching

Most of the GPU pricing data is updated once per day, with some providers updated hourly and some less frequently.

If you're sending a high volume of requests, we recommend:
- Cache responses for at least 15 minutes
- Store historical data locally for trend analysis

Pagination

The API returns paginated results with 10 items per page by default. Use the page and page_size parameters to navigate:

# Get page 2 with 100 results per page
curl -H "Authorization: Bearer YOUR_TOKEN" \
  "https://getdeploying.com/api/gpu-offerings?page=2&page_size=100"

Filtering Efficiently

For best performance:
- Use specific filters (gpu_model, provider) rather than fetching all data
- Filter on the API side rather than locally to reduce bandwidth
- Combine multiple filters to narrow results

Supported GPU Models

The API includes pricing for 96 GPU models:

GPU Model	Slug
AMD MI250	`amd-mi250`
AMD MI300X	`amd-mi300x`
AMD MI325X	`amd-mi325x`
AMD MI355X	`amd-mi355x`
AMD Radeon Pro V520	`amd-radeon-pro-v520`
Nvidia A10	`nvidia-a10`
Nvidia A100	`nvidia-a100`
Nvidia A10G	`nvidia-a10g`
Nvidia A16	`nvidia-a16`
Nvidia A30	`nvidia-a30`
Nvidia A40	`nvidia-a40`
Nvidia A4000	`nvidia-a4000`
Nvidia A4500	`nvidia-a4500`
Nvidia A5000	`nvidia-a5000`
Nvidia A800	`nvidia-a800`
Nvidia B100	`nvidia-b100`
Nvidia B200	`nvidia-b200`
Nvidia B300	`nvidia-b300`
Nvidia GB200	`nvidia-gb200`
Nvidia GH200	`nvidia-gh200`
Nvidia GT 710	`nvidia-gt710`
Nvidia GT 730	`nvidia-gt730`
Nvidia GTX 1050 Ti	`nvidia-gtx-1050-ti`
Nvidia GTX 1060	`nvidia-gtx-1060`
Nvidia GTX 1070	`nvidia-gtx-1070`
Nvidia GTX 1070 Ti	`nvidia-gtx-1070-ti`
Nvidia GTX 1080	`nvidia-gtx-1080`
Nvidia GTX 1080 Ti	`nvidia-gtx-1080-ti`
Nvidia GTX 1650	`nvidia-gtx-1650`
Nvidia GTX 1660	`nvidia-gtx-1660`
Nvidia GTX 1660 Super	`nvidia-gtx-1660-super`
Nvidia H100	`nvidia-h100`
Nvidia H20	`nvidia-h20`
Nvidia H200	`nvidia-h200`
Nvidia H800	`nvidia-h800`
Nvidia K620	`nvidia-k620`
Nvidia K80	`nvidia-k80`
Nvidia L4	`nvidia-l4`
Nvidia L40	`nvidia-l40`
Nvidia L40S	`nvidia-l40s`
Nvidia M4000	`nvidia-m4000`
Nvidia M60	`nvidia-m60`
Nvidia P100	`nvidia-p100`
Nvidia P1000	`nvidia-p1000`
Nvidia P4	`nvidia-p4`
Nvidia P40	`nvidia-p40`
Nvidia P4000	`nvidia-p4000`
Nvidia P5000	`nvidia-p5000`
Nvidia P600	`nvidia-p600`
Nvidia P6000	`nvidia-p6000`
Nvidia P620	`nvidia-p620`
Nvidia Quadro RTX 6000	`nvidia-rtx-6000`
Nvidia RTX 2060	`nvidia-rtx-2060`
Nvidia RTX 2060 Super	`nvidia-rtx-2060-super`
Nvidia RTX 2070	`nvidia-rtx-2070`
Nvidia RTX 2080	`nvidia-rtx-2080`
Nvidia RTX 2080 Ti	`nvidia-rtx-2080-ti`
Nvidia RTX 3050	`nvidia-rtx-3050`
Nvidia RTX 3060	`nvidia-rtx-3060`
Nvidia RTX 3060 Ti	`nvidia-rtx-3060-ti`
Nvidia RTX 3070	`nvidia-rtx-3070`
Nvidia RTX 3070 Ti	`nvidia-rtx-3070-ti`
Nvidia RTX 3080	`nvidia-rtx-3080`
Nvidia RTX 3080 Ti	`nvidia-rtx-3080-ti`
Nvidia RTX 3090	`nvidia-rtx-3090`
Nvidia RTX 3090 Ti	`nvidia-rtx-3090-ti`
Nvidia RTX 4000 Ada	`nvidia-rtx-4000-ada`
Nvidia RTX 4060	`nvidia-rtx-4060`
Nvidia RTX 4060 Ti	`nvidia-rtx-4060-ti`
Nvidia RTX 4070	`nvidia-rtx-4070`
Nvidia RTX 4070 Ti	`nvidia-rtx-4070-ti`
Nvidia RTX 4070 Ti Super	`nvidia-rtx-4070-ti-super`
Nvidia RTX 4080	`nvidia-rtx-4080`
Nvidia RTX 4090	`nvidia-rtx-4090`
Nvidia RTX 4500 Ada	`nvidia-rtx-4500-ada`
Nvidia RTX 5000	`nvidia-rtx-5000`
Nvidia RTX 5000 Ada	`nvidia-rtx-5000-ada`
Nvidia RTX 5060	`nvidia-rtx-5060`
Nvidia RTX 5060 Ti	`nvidia-rtx-5060-ti`
Nvidia RTX 5070	`nvidia-rtx-5070`
Nvidia RTX 5070 Ti	`nvidia-rtx-5070-ti`
Nvidia RTX 5080	`nvidia-rtx-5080`
Nvidia RTX 5090	`nvidia-rtx-5090`
Nvidia RTX 5880 Ada	`nvidia-rtx-5880-ada`
Nvidia RTX 6000 Ada	`nvidia-rtx-6000-ada`
Nvidia RTX A2000	`nvidia-a2000`
Nvidia RTX A6000	`nvidia-a6000`
Nvidia RTX PRO 4000	`nvidia-rtx-pro-4000`
Nvidia RTX Pro 4500	`nvidia-rtx-pro-4500`
Nvidia RTX Pro 5000	`nvidia-rtx-pro-5000`
Nvidia RTX Pro 6000	`nvidia-rtx-pro-6000`
Nvidia T1000	`nvidia-t1000`
Nvidia T4	`nvidia-t4`
Nvidia T4G	`nvidia-t4g`
Nvidia V100	`nvidia-v100`
Nvidia V100S	`nvidia-v100s`

View detailed GPU specifications →

Supported Providers

The API covers 64 cloud providers:

Provider	Slug
AceCloud	`acecloud`
Akamai Cloud	`akamai-cloud`
Alibaba Cloud	`alibaba-cloud`
Amazon Web Services	`aws`
Atlas Cloud	`atlas-cloud`
Backblaze	`backblaze`
Beam	`beam`
Bentaus	`bentaus`
Beyond.pl	`beyond-pl`
BreezeHost	`breezehost`
Bunny CDN	`bunnycdn`
Cerebrium	`cerebrium`
Cirrascale	`cirrascale`
Civo	`civo`
Cleura	`cleura`
Cloudflare	`cloudflare`
Cloudways	`cloudways`
Contabo	`contabo`
CoreWeave	`coreweave`
Crusoe	`crusoe`
CUDO Compute	`cudo-compute`
Database Mart	`database-mart`
deplo.io	`deploio`
DigitalOcean	`digitalocean`
Diploi	`diploi`
Elastx	`elastx`
Enverge	`enverge`
Exoscale	`exoscale`
Fal.ai	`fal-ai`
Firebase	`firebase`
FlexStack	`flexstack`
Flightcontrol	`flightcontrol`
FluidStack	`fluidstack`
Fly.io	`flyio`
Gcore	`gcore`
Google Cloud	`google-cloud`
GPUaaS	`gpuaas`
GPUhub	`gpuhub`
Green AI Cloud	`greenai-cloud`
Heroku	`heroku`
Hetzner	`hetzner`
Hexabyte	`hexabyte`
Hostiko	`hostiko`
Hostinger	`hostinger`
Hot Aisle	`hotaisle`
Hyperstack	`hyperstack`
Impossible Cloud	`impossible-cloud`
Koyeb	`koyeb`
Kuberns	`kuberns`
Lade	`lade`
Lambda Labs	`lambda-labs`
Leaseweb	`leaseweb`
Lyceum	`lyceum`
Massed Compute	`massed-compute`
Microsoft Azure	`microsoft-azure`
Nebius	`nebius`
Netlify	`netlify`
Nova Cloud	`nova-cloud`
Novita	`novita-ai`
Oblivus	`oblivus`
Oracle Cloud	`oracle-cloud`
OVHcloud	`ovh`
Packet·ai	`packet-ai`
Paperspace	`paperspace`
pushr.io	`pushr`
Railway	`railway`
Render	`render`
Replicate	`replicate`
Runcrate	`runcrate`
Runpod	`runpod`
Salad	`salad`
Scaleway	`scaleway`
Sesterce	`sesterce`
Sevalla	`sevalla`
Shadeform	`shadeform`
Supabase	`supabase`
SwissGPU	`swissgpu`
TensorDock	`tensordock`
TensorWave	`tensorwave`
Thalassa Cloud	`thalassa`
Theta EdgeCloud	`theta-edgecloud`
Thunder Compute	`thunder-compute`
Together	`together-ai`
UpCloud	`upcloud`
Vast.ai	`vast-ai`
Vercel	`vercel`
Verda	`verda`
Vultr	`vultr`
Wasabi	`wasabi`
Zeabur	`zeabur`
Zenlayer	`zenlayer`

View all providers with details →

Data Latency & Accuracy

Snapshot frequency: Cloud pricing and availability can fluctuate in real-time. Update frequencies vary by provider, but we refresh most pricing data daily. Some providers update hourly, and others on a less frequent schedule. We prioritize our update cadence based on provider popularity, data source availability, and other operational factors.
Non-binding: All prices returned by the API are estimates for informational purposes only and do not constitute a binding offer to sell compute.
Final billing: The final cost is determined strictly by the provider at the moment of provisioning. We strongly recommend performing a dry-run or checking the provider's console before launching high-volume workloads.
Some providers may have regional price variations and other pricing factors not reflected in our data.
Contact us if you notice any discrepancies.

Legal & Usage

Use of the API is subject to our Terms and Conditions.

Support

You can reach us anytime at [email protected].