> ## Documentation Index
> Fetch the complete documentation index at: https://docs.compute-desk.com/llms.txt
> Use this file to discover all available pages before exploring further.

# GPU Models

> Get list of all GPU models with pricing statistics and availability

## Example

List every GPU model with pricing statistics and availability:

```bash theme={null}
curl -H "Authorization: Bearer $TOKEN" \
  "https://data-api.compute-index.com/v1/gpus"
```


## OpenAPI

````yaml pricing/openapi.json GET /v1/gpus
openapi: 3.1.0
info:
  title: GPU Pricing API
  description: |2-

        **GPU Pricing API** provides real-time and historical pricing data
        for GPU compute across 50+ cloud providers and GPU marketplaces.

        ## Features
        - Search current prices across vendors
        - Historical price trends
        - GPU transaction data
        - **Informational Price Index** — EWMA-smoothed composite indices by GPU family, region, and contract type
        - **Transaction Price Index** — smoothed indices derived from verified GPU transactions
        - **Custom Index** — EWMA-smoothed H100 sub-model indices by region, contract type, and vendor category
        - Global region coverage (US, EU, APAC)
        - GPU availability tracking
        - Scope-based API key access control

        ## Authentication
        Send your token as a Bearer token in the `Authorization` header on every request:
        ```
        Authorization: Bearer YOUR_TOKEN
        ```
        Example:
        ```bash
        curl -H "Authorization: Bearer $TOKEN" "https://data-api.compute-index.com/v1/vendors"
        ```
        Tokens are issued by Compute Index (david@compute-index.com); long-lived, treat as secrets.

        > The legacy `X-API-Key` header is deprecated — use the `Authorization: Bearer` header above.

        ## Rate Limits
        - **Free tier**: 100 requests/minute, 10,000/day
        - **Pro tier**: 1,000 requests/minute, 100,000/day
        - **Enterprise**: Custom limits

        ## Data Coverage
        - 50+ vendors (AWS, Azure, GCP, Oracle, CoreWeave, Lambda, RunPod, Vast.AI, FluidStack, Vultr, etc.)
        - 30M+ historical pricing records
        - Updated multiple times daily

        ## Support
        - Support: david@compute-index.com
        
  contact:
    name: API Support
    email: david@compute-index.com
  license:
    name: Commercial License
    url: https://compute-desk.com/license
  version: 1.0.0
servers:
  - url: https://data-api.compute-index.com
security: []
paths:
  /v1/gpus:
    get:
      tags:
        - Metadata
      summary: List all GPU models
      description: Get list of all GPU models with pricing statistics and availability
      operationId: list_gpu_models_v1_gpus_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GPUModelListResponse'
      security:
        - HTTPBearer: []
components:
  schemas:
    GPUModelListResponse:
      properties:
        data:
          items:
            $ref: '#/components/schemas/GPUModelResponse'
          type: array
          title: Data
        total_count:
          type: integer
          title: Total Count
      type: object
      required:
        - data
        - total_count
      title: GPUModelListResponse
      description: Response schema for list of GPU models
    GPUModelResponse:
      properties:
        gpu_canonical_name:
          type: string
          title: Gpu Canonical Name
          description: Canonical GPU identifier (e.g., nvidia-h100-sxm5-80gb)
        gpu_manufacturer:
          type: string
          title: Gpu Manufacturer
        gpu_model_variants:
          items:
            type: string
          type: array
          title: Gpu Model Variants
          description: GPU model name variants across vendors (e.g., H100, H100 SXM5)
        total_record_count:
          type: integer
          title: Total Record Count
          description: Total records (current + historical)
        open_record_count:
          type: integer
          title: Open Record Count
          description: Current price records (valid_to IS NULL)
        vendor_count:
          type: integer
          title: Vendor Count
        region_count:
          type: integer
          title: Region Count
        min_price:
          type: number
          title: Min Price
        max_price:
          type: number
          title: Max Price
        avg_price:
          type: number
          title: Avg Price
        contract_types:
          items:
            type: string
          type: array
          title: Contract Types
          description: Available contract types for this GPU
        contract_terms:
          items:
            type: string
          type: array
          title: Contract Terms
          description: Available contract terms for this GPU (non-null only)
        vendors:
          items:
            type: string
          type: array
          title: Vendors
          description: Vendors offering this GPU
      type: object
      required:
        - gpu_canonical_name
        - gpu_manufacturer
        - gpu_model_variants
        - total_record_count
        - open_record_count
        - vendor_count
        - region_count
        - min_price
        - max_price
        - avg_price
        - contract_types
        - contract_terms
        - vendors
      title: GPUModelResponse
      description: Response schema for GPU model metadata
  securitySchemes:
    HTTPBearer:
      type: http
      scheme: bearer

````