{
  "listings": [
    {
      "slug": "beam",
      "name": "Beam",
      "company": "Smartshare, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "beam machine list shows live serverless availability and beam pool has lists provider, region, resources and cost with a --max-spend cap; beam machine reserve --yes takes the cheapest offer. No provisioning time or capacity error format is documented.",
      "source": "https://docs.beam.cloud/v2/environment/gpu",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/beam"
    },
    {
      "slug": "coreweave",
      "name": "CoreWeave",
      "company": "CoreWeave, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "The beta Capacity Finder API (POST /v1beta1/capacity/availability:get) ranks zones for spot node pools only, from cached data that neither reserves nor guarantees; on-demand capacity is a quota question with sales. Node pool conditions report Sufficient or partial capacity after the fact.",
      "source": "https://docs.coreweave.com/platform/capacity-plans/capacity-finder-api.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/coreweave"
    },
    {
      "slug": "crusoe-cloud",
      "name": "Crusoe Cloud",
      "company": "Crusoe Technologies LLC",
      "grade": "B",
      "fit": "caveat",
      "why": "GET /v1/capacities?product_name=a100.8x\u0026location=... reports availability per type and location before a create, and creates return an operation to poll. Requests are HMAC-signed, no idempotency key exists, and the docs say quotas do not guarantee capacity.",
      "source": "https://docs.crusoe.ai/reference/api/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/crusoe-cloud"
    },
    {
      "slug": "gpusmarket",
      "name": "GPUsMarket",
      "company": "Tyga.Cloud Ltd",
      "grade": "E",
      "fit": "caveat",
      "why": "GET /marketplace/search takes gpu, maxPrice and minVram, /gpu/cheapest?vram=24 picks the cheapest, and /gpu/deploy claims about 30 s provisioning. 502 means the host is offline and the agent rents another; completeness of search results is not documented.",
      "source": "https://gpusmarket.com/llms.txt",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/gpusmarket"
    },
    {
      "slug": "hyperbolic",
      "name": "Hyperbolic",
      "company": "Hyperbolic Labs, Inc.",
      "grade": "E",
      "fit": "caveat",
      "why": "GET /v2/on-demand/rentals/options lists rentable configurations and the docs say capacity changes hour to hour; sold-out alerts are email only and personal accounts only. Create has no idempotency key, and an instance can sit pending up to the 3 hour provisioning timeout before auto-termination.",
      "source": "https://hyperbolic.ai/docs/api-reference/rentals/get-a-list-of-rental-options",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/hyperbolic"
    },
    {
      "slug": "lambda",
      "name": "Lambda Cloud",
      "company": "Lambda, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "GET /instance-types returns regions_with_capacity_available and launch fails with the structured code instance-operations/launch/insufficient-capacity. Launch has no idempotency key, 429s arrive after five launches a minute, and users report capacity gone for days with scripting retries the only remedy (acc-30).",
      "source": "https://docs.lambda.com/api/cloud/spec.json",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/lambda"
    },
    {
      "slug": "massed-compute",
      "name": "Massed Compute",
      "company": "Massed Compute, Inc.",
      "grade": "E",
      "fit": "caveat",
      "why": "GET /gpu-inventory lists available GPU configurations before launch, and launch returns 402 until credit and auto-recharge are set. No idempotency key, no documented capacity error shape, and no timing for reaching SSH.",
      "source": "https://vm-docs.massedcompute.com/api/v1",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/massed-compute"
    },
    {
      "slug": "nebius-ai-cloud",
      "name": "Nebius AI Cloud",
      "company": "Nebius B.V.",
      "grade": "BB",
      "fit": "caveat",
      "why": "list-platforms shows the platforms and presets a project can use and X-Idempotency-Key makes a retried create safe, but there is no capacity count per region, quota overruns fail with QuotaExceeded, and creates return an operation to poll.",
      "source": "https://docs.nebius.com/compute/virtual-machines/list-platforms",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/nebius-ai-cloud"
    },
    {
      "slug": "runpod",
      "name": "Runpod",
      "company": "Runpod, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "List GPU types and data centres return pricing with availability (HIGH to NONE) before a Pod create, and 80 GB cards now arrive in minutes (acc-02). A Pod takes one GPU type so fallback is the caller's loop, and there is no idempotency key.",
      "source": "https://docs.runpod.io/api-reference-v2/catalog/list-gpu-types",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/runpod"
    },
    {
      "slug": "thunder-compute",
      "name": "Thunder Compute",
      "company": "Thunder GPU, Inc.",
      "grade": "D",
      "fit": "caveat",
      "why": "GET availability and GET /v2/specs list GPU types and current availability before create, and creation fails when a type is sold out. No idempotency key, no capacity error shape documented, and no timing to SSH.",
      "source": "https://www.thundercompute.com/docs/api-reference/utilities/get-gpu-availability",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/thunder-compute"
    },
    {
      "slug": "together-gpu-clusters",
      "name": "Together GPU Clusters",
      "company": "Together Computer, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "GET /v1/compute/regions lists regions, instance types and driver versions but no prices or capacity counts, create fails with a structured error when credits are short, and there is no idempotency key; Ready arrives in 10 minutes to an hour.",
      "source": "https://docs.together.ai/docs/gpu-clusters-management",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/together-gpu-clusters"
    },
    {
      "slug": "vast-ai",
      "name": "Vast.ai",
      "company": "Vast.ai Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "POST /api/v0/bundles filters has by gpu_name, num_gpus, reliability and price, but repeated identical queries returned a random 10 to 30 percent of matching has (acc-24), unknown fields silently dropped the gpu_name filter (acc-26), and a reservation hung at provisioning four times (acc-19).",
      "source": "https://docs.vast.ai/api-reference/search/search-offers",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/vast-ai"
    },
    {
      "slug": "verda",
      "name": "Verda",
      "company": "DataCrunch Oy",
      "grade": "C",
      "fit": "caveat",
      "why": "GET /v1/instance-availability lists what each location can launch and POST /v1/instances returns 503 service_unavailable when it cannot, which is a structured capacity error. There is no idempotency key, so a retried launch can start a second billed instance.",
      "source": "https://docs.verda.com/llms-full.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/verda"
    },
    {
      "slug": "baseten",
      "name": "Baseten",
      "company": "Baseten Labs, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "Fixed instance-type catalogue with no availability call, offer search or price comparison; Baseten places replicas across its own multi-cloud capacity.",
      "source": "https://docs.baseten.co/deployment/resources",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/baseten"
    },
    {
      "slug": "cerebrium",
      "name": "Cerebrium",
      "company": "Cerebrium Inc.",
      "grade": "C",
      "fit": "no",
      "why": "No availability call or offer search; capacity is a static GPU-by-region table and a preference list of up to five GPU types the platform falls back through.",
      "source": "https://cerebrium.ai/docs/hardware/using-gpus",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cerebrium"
    },
    {
      "slug": "cloud-run-gpus",
      "name": "Cloud Run GPUs",
      "company": "Google LLC",
      "grade": "B",
      "fit": "no",
      "why": "Two GPU types in a fixed region list with a default quota of 3 GPUs a region; no availability call, offer search or price comparison.",
      "source": "https://docs.cloud.google.com/run/docs/configuring/services/gpu",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/cloud-run-gpus"
    },
    {
      "slug": "hugging-face-inference-endpoints",
      "name": "Hugging Face Inference Endpoints",
      "company": "Hugging Face, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "Fixed instance tiles per cloud and region, greyed out when unavailable, and a provider list with status; no cross-vendor search, price cap or capacity error for a VM.",
      "source": "https://huggingface.co/docs/inference-endpoints/guides/configuration",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/hugging-face-inference-endpoints"
    },
    {
      "slug": "koyeb",
      "name": "Koyeb",
      "company": "Koyeb SAS",
      "grade": "D",
      "fit": "no",
      "why": "Fixed GPU instance types in specific regions with no availability call or price search.",
      "source": "https://www.koyeb.com/docs/reference/instances",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/koyeb"
    },
    {
      "slug": "modal",
      "name": "Modal",
      "company": "Modal Labs, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "No availability call or offer search; the agent passes a GPU priority list and Modal schedules on whatever is free, with region selection as the only placement knob.",
      "source": "https://modal.com/docs/guide/gpu",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/modal"
    },
    {
      "slug": "northflank",
      "name": "Northflank",
      "company": "Northflank Ltd",
      "grade": "C",
      "fit": "no",
      "why": "GPU models are a dropdown per region with VRAM and price; no availability call, cross-region search or capacity error is documented.",
      "source": "https://northflank.com/docs/v1/application/gpu-workloads/deploy-gpus-on-northflank-cloud.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/northflank"
    },
    {
      "slug": "replicate-deploy",
      "name": "Replicate Deployments",
      "company": "Replicate, LLC",
      "grade": "B",
      "fit": "no",
      "why": "Hardware is a fixed SKU list chosen per deployment; no availability call, offer search or capacity error.",
      "source": "https://replicate.com/docs/topics/models/hardware",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/replicate-deploy"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 10,
    "after": [
      "gpu-compute.training-run",
      "gpu-compute.self-hosted-llm-server",
      "gpu-compute.batch-job"
    ],
    "area": "models",
    "asks": [
      "find me the cheapest available A100 80GB right now",
      "is an H100 available anywhere, launch one if so",
      "keep trying until a GPU frees up"
    ],
    "before": [
      "gpu-compute.agent-provisioned-compute"
    ],
    "blockers": [
      "search endpoint returns a random 10 to 30 percent of matching has, so the cheapest offer is often missing",
      "provisioning hangs with no error and the deposit is spent on nothing",
      "sold out for days and no queue or notification, only retrying",
      "launch has no idempotency key, so a retried call after a timeout starts a second billed machine",
      "availability claimed in marketing but on-demand refused after sign-up"
    ],
    "capabilities": [
      "compute.gpu",
      "compute.marketplace"
    ],
    "category": "gpu-compute",
    "categoryName": "GPU \u0026 serverless compute",
    "checked": "2026-11-12",
    "companies": {
      "fit": 0,
      "fitWithLimit": 13,
      "tagged": 22
    },
    "competition": "none",
    "fits": null,
    "fitsWithLimit": [
      "beam",
      "coreweave",
      "crusoe-cloud",
      "gpusmarket",
      "hyperbolic",
      "lambda",
      "massed-compute",
      "nebius-ai-cloud",
      "runpod",
      "thunder-compute",
      "together-gpu-clusters",
      "vast-ai",
      "verda"
    ],
    "id": "gpu-compute.find-and-provision",
    "listings": {
      "caveat": 13,
      "no": 8,
      "notRead": 0,
      "tagged": 22,
      "unchecked": 0,
      "yes": 0
    },
    "name": "Find GPU capacity at a price and get a machine running",
    "status": "draft",
    "success": "A list or availability call returns the complete set of has or regions with capacity, the launch call either succeeds or returns a structured capacity error, and the instance becomes SSH-reachable or Ready. Measured: the set comes from one list or availability call, the launch result within 30 seconds, and the instance is SSH-reachable or Ready within 15 minutes.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/gpu-compute.find-and-provision.json",
    "weight": 14,
    "weightBasis": "10 of 48 accounts are about getting a machine at all: capacity gone for days, provisioning that hangs, search results that are a random subset, availability that changed between list and launch."
  }
}
