{
  "listings": [
    {
      "slug": "baseten",
      "name": "Baseten",
      "company": "Baseten Labs, Inc.",
      "grade": "B",
      "fit": "yes",
      "why": "Model Library presets serve named Hub models through vLLM's OpenAI-compatible server on a stated GPU, and BIS-LLM deployments expose /v1/chat/completions; deployments are deleted through the Management API. BIS-LLM itself needs support to enable.",
      "source": "https://docs.baseten.co/examples/models/embedding/nemotron-3-embed",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/baseten"
    },
    {
      "slug": "hugging-face-inference-endpoints",
      "name": "Hugging Face Inference Endpoints",
      "company": "Hugging Face, Inc.",
      "grade": "B",
      "fit": "yes",
      "why": "Pick a Hub model, a cloud instance and the vLLM, SGLang or TGI engine and the endpoint serves an OpenAI-compatible API; tensor_parallel_size defaults to the instance's GPU count, instances run to 8x H200, and the management API deletes the endpoint.",
      "source": "https://huggingface.co/docs/inference-endpoints/engines/vllm",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/hugging-face-inference-endpoints"
    },
    {
      "slug": "koyeb",
      "name": "Koyeb",
      "company": "Koyeb SAS",
      "grade": "D",
      "fit": "yes",
      "why": "The vLLM One-Click app deploys an OpenAI-compatible server on a GPU instance with the Hub model set in the command args, HF_TOKEN and VLLM_API_KEY as environment variables; GPU instances run from 20 GB to 8x H200, and a service is deleted by one API call.",
      "source": "https://www.koyeb.com/deploy/vllm",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/koyeb"
    },
    {
      "slug": "beam",
      "name": "Beam",
      "company": "Smartshare, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "The SGLang example serves Qwen2.5-7B-Instruct on an H100 Pod with an OpenAI-compatible API, but it is a code example, not a one-step template: the agent writes app.py with the image and server command. Pods stop after 600 s idle by default.",
      "source": "https://docs.beam.cloud/v2/examples/sglang",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/beam"
    },
    {
      "slug": "cerebrium",
      "name": "Cerebrium",
      "company": "Cerebrium Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "Every endpoint can answer /chat/completions and a vLLM example exists, but the agent writes the handler and image itself; there is no one-step template taking only a model name. A100 and above need the Standard plan.",
      "source": "https://cerebrium.ai/docs/endpoints/openai-compatible-endpoints",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cerebrium"
    },
    {
      "slug": "cloud-run-gpus",
      "name": "Cloud Run GPUs",
      "company": "Google LLC",
      "grade": "B",
      "fit": "caveat",
      "why": "An Ollama or vLLM container on an L4 serves an OpenAI-compatible API and a user found spin-up fast and the service easy (acc-35), but the agent builds the image itself and only 24 GB or 96 GB single-GPU instances exist, so models above about 70B do not fit.",
      "source": "https://docs.cloud.google.com/run/docs/configuring/services/gpu-best-practices",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/cloud-run-gpus"
    },
    {
      "slug": "coreweave",
      "name": "CoreWeave",
      "company": "CoreWeave, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "Dedicated Inference deployments run dynamo-vllm or vllm behind an OpenAI-compatible endpoint, but weights must first be uploaded to an AI Object Storage bucket (no Hub pulls), the API is v1alpha1, and access is sales-gated.",
      "source": "https://docs.coreweave.com/products/inference/models.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": "Self-serve deployments expose an OpenAI-compatible gateway for a listed base model or a Hugging Face LoRA adapter, billed per GPU-hour; an arbitrary Hub model goes on a VM where the agent installs vLLM over SSH.",
      "source": "https://docs.crusoe.ai/self-serve-deployments/overview",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/crusoe-cloud"
    },
    {
      "slug": "gpusmarket",
      "name": "GPUsMarket",
      "company": "Tyga.Cloud Ltd",
      "grade": "E",
      "fit": "caveat",
      "why": "Renting a listing or deploying a pod with models [\"llama3.3\"] returns a per-rental token and an OpenAI-compatible /v1/chat/completions proxy; stop ends billing. Prompts pass through the host's machine and the reference says not to send confidential data.",
      "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": "Ubuntu with drivers and Docker preinstalled; a user rented 4x H100, pip-installed vLLM over SSH and served Llama 4 Scout with TP=4 (acc-44). No vLLM or Ollama template, so the engine and weights are installed by hand, and the VM bills hourly until terminated.",
      "source": "https://hyperbolic.ai/docs/on-demand/overview",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/hyperbolic"
    },
    {
      "slug": "lambda",
      "name": "Lambda Cloud",
      "company": "Lambda, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "Lambda Stack ships CUDA, PyTorch and Docker and guides cover vLLM and Ollama, but the agent installs the engine and weights over SSH; there is no serving template and the VM bills per minute until terminated.",
      "source": "https://docs.lambda.com/public-cloud/on-demand/",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/lambda"
    },
    {
      "slug": "massed-compute",
      "name": "Massed Compute",
      "company": "Massed Compute, Inc.",
      "grade": "E",
      "fit": "caveat",
      "why": "A VM with a chosen image and SSH can run vLLM or Ollama, but no engine template or OpenAI-compatible preset appears in the API or MCP tool list; the agent installs the server itself and the VM bills until terminated.",
      "source": "https://vm-docs.massedcompute.com/api/v1",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/massed-compute"
    },
    {
      "slug": "modal",
      "name": "Modal",
      "company": "Modal Labs, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "The vLLM example serves a Hub model behind /v1/chat/completions on H200s with scaledown_window set to 15 minutes, but it is a Python app the agent copies and deploys, not a one-step template; cold starts are tens of seconds to minutes, about ten from cache.",
      "source": "https://modal.com/docs/examples/llm_inference",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/modal"
    },
    {
      "slug": "nebius-ai-cloud",
      "name": "Nebius AI Cloud",
      "company": "Nebius B.V.",
      "grade": "BB",
      "fit": "caveat",
      "why": "A Serverless AI endpoint runs a vLLM container on a gpu-h100-sxm preset behind a managed HTTPS URL with a token, and stop or delete ends charges; the agent supplies the container and model settings, and there is no engine template taking only a model name.",
      "source": "https://docs.nebius.com/serverless/endpoints/manage",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/nebius-ai-cloud"
    },
    {
      "slug": "northflank",
      "name": "Northflank",
      "company": "Northflank Ltd",
      "grade": "C",
      "fit": "caveat",
      "why": "The host-a-model guide deploys any serving image (vLLM, Ollama) as a GPU service with ports, secrets and health checks, but the agent supplies the image and command; no engine template takes a model name.",
      "source": "https://northflank.com/docs/v1/application/use-cases/host-a-model-on-gpus.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/northflank"
    },
    {
      "slug": "runpod",
      "name": "Runpod",
      "company": "Runpod, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "The vLLM worker serves a Hub model with OpenAI-compatible responses from a template, but its hub defaults (MAX_NUM_SEQS 256) made an 8B model OOM on an RTX 5090, relaunch in eager mode at half throughput and restart on the same footprint (acc-09).",
      "source": "https://docs.runpod.io/serverless/vllm/overview",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/runpod"
    },
    {
      "slug": "thunder-compute",
      "name": "Thunder Compute",
      "company": "Thunder GPU, Inc.",
      "grade": "D",
      "fit": "caveat",
      "why": "tnr create --gpu a100xl --template ollama gives an instance with Ollama preinstalled and guides run DeepSeek R1 70B and GPT-OSS 120B in minutes, but the model is pulled by hand over SSH and no vLLM template or OpenAI-compatible URL is documented.",
      "source": "https://www.thundercompute.com/docs/guides/gpt-oss-running-locally-on-thunder-compute",
      "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": "A Kubernetes cluster can run vLLM, but the agent writes the manifest, the smallest unit is 8 GPUs, and provisioning takes 10 minutes to an hour; no engine template or OpenAI endpoint is provided by the product.",
      "source": "https://docs.together.ai/docs/gpu-clusters-overview",
      "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": "A recommended vLLM template plus a search filter gets a model server on a rented H100, which a user did to measure gpt-oss-20b refusal rates (acc-21). Prompts pass through the host's machine unless Secure Cloud is filtered, and the instance bills until destroyed.",
      "source": "https://docs.vast.ai/guides/instances/choosing/templates",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/vast-ai"
    },
    {
      "slug": "verda",
      "name": "Verda",
      "company": "DataCrunch Oy",
      "grade": "C",
      "fit": "caveat",
      "why": "The Serverless Containers vLLM quickstart serves a Hub model behind an OpenAI-compatible endpoint from a container image on an L40S; on a VM the images are Ubuntu or JupyterLab and the engine is installed by hand. Deleting the deployment or instance stops charges.",
      "source": "https://docs.verda.com/containers/tutorials/deploy-with-vllm-quick",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/verda"
    },
    {
      "slug": "replicate-deploy",
      "name": "Replicate Deployments",
      "company": "Replicate, LLC",
      "grade": "B",
      "fit": "no",
      "why": "A deployment serves a Cog model behind Replicate's prediction API; no OpenAI-compatible /v1/chat/completions route or vLLM template appears in the docs index, so the success criterion cannot be met.",
      "source": "https://replicate.com/docs/llms.txt",
      "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": 7,
    "after": [
      "inference.tool-loop",
      "inference.harness-compat",
      "agent-harnesses.local-model",
      "decision-models.run-on-own-hardware"
    ],
    "area": "models",
    "asks": [
      "spin up gpt-oss-20b on an H100 with vLLM and give me the URL",
      "run Llama 4 Scout on 4 GPUs behind an API",
      "host this model privately for my agents instead of paying per token"
    ],
    "before": [
      "gpu-compute.find-and-provision",
      "open-weights.big-model-on-big-box",
      "open-weights.tool-calling-assistant"
    ],
    "blockers": [
      "no template for the engine, so the agent must install CUDA, vLLM and the weights over SSH",
      "peer host hardware with firmware-capped clocks or that cannot pull images",
      "prompts and outputs pass through an individual host's machine, so private data is out",
      "an idle machine bills by the hour until destroyed, with no scale to zero"
    ],
    "capabilities": [
      "compute.gpu",
      "compute.containers",
      "compute.endpoints"
    ],
    "category": "gpu-compute",
    "categoryName": "GPU \u0026 serverless compute",
    "checked": "2026-11-12",
    "companies": {
      "fit": 3,
      "fitWithLimit": 17,
      "tagged": 24
    },
    "competition": "few",
    "fits": [
      "baseten",
      "hugging-face-inference-endpoints",
      "koyeb"
    ],
    "fitsWithLimit": [
      "beam",
      "cerebrium",
      "cloud-run-gpus",
      "coreweave",
      "crusoe-cloud",
      "gpusmarket",
      "hyperbolic",
      "lambda",
      "massed-compute",
      "modal",
      "nebius-ai-cloud",
      "northflank",
      "runpod",
      "thunder-compute",
      "together-gpu-clusters",
      "vast-ai",
      "verda"
    ],
    "id": "gpu-compute.self-hosted-llm-server",
    "listings": {
      "caveat": 17,
      "no": 1,
      "notRead": 0,
      "tagged": 24,
      "unchecked": 0,
      "yes": 3
    },
    "name": "Run an open model as my own OpenAI-compatible server for a while",
    "status": "draft",
    "success": "An OpenAI-compatible /v1/chat/completions URL answers correctly after the launch call, with model weights loaded from a template or one install step, and the machine is destroyed when done. Measured: the URL answers within 15 minutes of the launch call, and the machine is destroyed by one call.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/gpu-compute.self-hosted-llm-server.json",
    "weight": 14,
    "weightBasis": "7 of 48 accounts stand up vLLM or Ollama on a rented machine to serve a model to their own tools; two of them left for local hardware on cost."
  }
}
