> ## Documentation Index > Fetch the complete documentation index at: https://vastai-80aa3a82-auto-openapi-preview-pr-5002.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Get Current GPU Supply Snapshot > Returns a current point-in-time snapshot of all GPU types with counts, utilization, and pricing percentiles. ## OpenAPI ````yaml /api-reference/openapi.yaml get /api/v0/metrics/gpu/current openapi: 3.1.0 info: title: Vast.ai API description: >- Vast.ai REST API for managing GPU cloud instances, machine operations, and AI/ML workflows. ## AI Agent Quick-Start Install the CLI skill for your agent (Claude Code, Cursor, Windsurf, etc.): npx skills add vast-ai/vast-cli CLI reference: https://raw.githubusercontent.com/vast-ai/vast-cli/master/vastai/SKILL.md SDK reference: https://raw.githubusercontent.com/vast-ai/vast-cli/master/vastai_sdk/SKILL.md ## Auth All endpoints require `Authorization: Bearer $VAST_API_KEY`. Get your key at: https://cloud.vast.ai/manage-keys/ ## Key Quirks - `gpu_ram` in CLI = GB; in REST API = MB (CLI auto-converts) - SSH keys must be registered BEFORE creating an instance (VM: no recovery; Docker: can add post-create) - `onstart` field is limited to 4048 characters -- gzip+base64 for longer scripts - `POST /api/v0/asks/{id}/` (create instance) returns `new_contract` as the instance ID, not `id` - Poll trap: if `actual_status` becomes `exited`, `unknown`, or `offline` it will never reach `running` -- destroy and retry version: 1.0.0 contact: name: Vast.ai Support url: https://discord.gg/vast license: name: Vast.ai Terms of Service url: https://vast.ai/terms/ servers: - url: https://console.vast.ai description: Production server security: - BearerAuth: [] paths: /api/v0/metrics/gpu/current: get: tags: - Machines summary: Get Current GPU Supply Snapshot description: >- Returns a current point-in-time snapshot of all GPU types with counts, utilization, and pricing percentiles. operationId: getCurrentGPUSupplySnapshot parameters: - name: verified in: query required: false description: Filter by verification status schema: type: string enum: - 'yes' - 'no' - all default: 'yes' - name: hosting_type in: query required: false description: Filter by hosting type schema: type: string enum: - all - secure_cloud - community default: all - name: num_gpus in: query required: false description: GPU count bucket or "all" for true population schema: type: string default: all responses: '200': description: >- Success. Returns `{success: true, gpus: [{gpu_name, total, available, rented_verified, avail_verified, rented_unverified, avail_unverified, usage, usage_30d, dlperf, tflops, price_p10, price_p25, price_median, price_p75, price_p90, tflops_per_dollar, dlperf_per_dollar}]}`. If the user is a host with no active machines, returns `{success: true, gpus: [], needs_machine: true}`. content: application/json: schema: type: object properties: success: type: boolean description: Always true on success needs_machine: type: boolean description: >- True when the caller is a host with no active machines; gpus will be empty gpus: type: array description: >- One entry per GPU type with >= 10 total GPUs, sorted by total descending items: type: object properties: gpu_name: type: string description: GPU model name, e.g. 'RTX 4090' total: type: integer description: Total machine/rig count available: type: integer description: Available (unrented) machine count rented_verified: type: integer description: Rented verified machine count avail_verified: type: integer description: Available verified machine count rented_unverified: type: integer description: Rented unverified machine count avail_unverified: type: integer description: Available unverified machine count total_gpus: type: integer description: Raw total GPU count available_gpus: type: integer description: Raw available GPU count rented_verified_gpus: type: integer description: Raw rented verified GPU count avail_verified_gpus: type: integer description: Raw available verified GPU count rented_unverified_gpus: type: integer description: Raw rented unverified GPU count avail_unverified_gpus: type: integer description: Raw available unverified GPU count bucket_size: type: integer description: >- GPUs per rig for the queried num_gpus bucket; 1 when num_gpus=all usage: type: number description: Current utilization percentage (0-100) usage_30d: type: number description: 30-day average utilization percentage dlperf: type: number description: 90th-percentile deep-learning performance score tflops: type: number description: 90th-percentile TFLOPS price_p10: type: number description: 10th-percentile rental price per GPU-hour price_p25: type: number description: 25th-percentile rental price per GPU-hour price_median: type: number description: Median rental price per GPU-hour price_p75: type: number description: 75th-percentile rental price per GPU-hour price_p90: type: number description: 90th-percentile rental price per GPU-hour tflops_per_dollar: type: number description: TFLOPS divided by median price (performance/dollar) dlperf_per_dollar: type: number description: DL performance divided by median price example: success: true gpus: - gpu_name: RTX 4090 total: 1200 available: 400 rented_verified: 650 avail_verified: 300 rented_unverified: 150 avail_unverified: 100 total_gpus: 1200 available_gpus: 400 rented_verified_gpus: 650 avail_verified_gpus: 300 rented_unverified_gpus: 150 avail_unverified_gpus: 100 bucket_size: 1 usage: 66.7 usage_30d: 64.2 dlperf: 72.3 tflops: 82.6 price_p10: 0.29 price_p25: 0.35 price_median: 0.45 price_p75: 0.59 price_p90: 0.74 tflops_per_dollar: 183.6 dlperf_per_dollar: 160.7 '400': description: >- Invalid query parameter. "verified must be 'yes', 'no', or 'all'" or "hosting_type must be 'all', 'secure_cloud', or 'community'" content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: 'Caller is not a host or admin: "Host or admin access required"' content: application/json: schema: $ref: '#/components/schemas/Error' security: - BearerAuth: [] components: schemas: Error: type: object properties: error: type: string msg: type: string securitySchemes: BearerAuth: type: http scheme: bearer description: API key must be provided in the Authorization header ````