{
  "listings": [
    {
      "slug": "amazon-bedrock-customization",
      "name": "Amazon Bedrock model customisation",
      "company": "Amazon Web Services, Inc.",
      "grade": "A",
      "fit": "caveat",
      "why": "On-demand deployment bills only for use and is created by API with a client request token, but it covers four Nova models and Llama 3.3 70B; acc-25 found imported models keep billing storage after clean-up.",
      "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/deploy-custom-model-on-demand.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/amazon-bedrock-customization"
    },
    {
      "slug": "azure-foundry-fine-tuning",
      "name": "Microsoft Foundry fine-tuning (Azure OpenAI)",
      "company": "Microsoft Corporation",
      "grade": "C",
      "fit": "caveat",
      "why": "The cost guide states the hourly hosting fee (720 hours a month in its example) and that Developer deployments vanish after 24 hours, but no idle-free per-token option lasts, and acc-26 and acc-27 found no pause and minutes-long redeploys.",
      "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/fine-tuning-cost-management",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/azure-foundry-fine-tuning"
    },
    {
      "slug": "fireworks-fine-tuning",
      "name": "Fireworks AI Fine-tuning",
      "company": "Fireworks.ai, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Serverless LoRA has no deployment to pay for and loads in under five minutes, but only for GLM 5.3 Flash; every other tuned model goes to on-demand GPUs billed by the hour.",
      "source": "https://docs.fireworks.ai/serverless/specialized-model-inference/overview.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/fireworks-fine-tuning"
    },
    {
      "slug": "nebius-token-factory-fine-tuning",
      "name": "Nebius Token Factory fine-tuning",
      "company": "Nebius B.V.",
      "grade": "D",
      "fit": "caveat",
      "why": "Tuned models run only on dedicated endpoints, which bill while replicas are ready; the hosting price sits in a console page robots.txt disallows, so the docs state no hourly fee or idle rule.",
      "source": "https://docs.tokenfactory.nebius.com/ai-models-inference/dedicated-endpoints/custom-weights.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/nebius-token-factory-fine-tuning"
    },
    {
      "slug": "together-fine-tuning",
      "name": "Together AI Fine-tuning",
      "company": "Together Computer, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "The docs state that dedicated inference bills per minute per running replica even when idle and that scaling to zero stops billing, but no per-token serving exists for tuned models and no time to scale back up was found.",
      "source": "https://docs.together.ai/docs/fine-tuning/deployment.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/together-fine-tuning"
    },
    {
      "slug": "vertex-ai-tuning",
      "name": "Vertex AI Gemini tuning",
      "company": "Google LLC",
      "grade": "B",
      "fit": "caveat",
      "why": "Tuned endpoints bill per prediction token with no hosting fee on the pricing page, but neither page read states a storage fee or whether idle tuned endpoints are deleted.",
      "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/vertex-ai-tuning"
    },
    {
      "slug": "tinker",
      "name": "Tinker",
      "company": "Thinking Machines Labs, Inc.",
      "grade": "D",
      "fit": "unchecked",
      "why": "Sampling and checkpoint storage prices are on the docs site, which was not read because the Service Terms bar automated scraping of the documentation.",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/tinker"
    },
    {
      "slug": "axolotl",
      "name": "Axolotl",
      "company": "Axolotl AI",
      "grade": "B",
      "fit": "no",
      "why": "Not a hosting service.",
      "source": "https://docs.axolotl.ai/docs/installation.html",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/axolotl"
    },
    {
      "slug": "unsloth",
      "name": "Unsloth",
      "company": "Unsloth",
      "grade": "C",
      "fit": "no",
      "why": "Not a hosting service; serving cost depends on wherever the export runs.",
      "source": "https://unsloth.ai/docs/get-started/fine-tuning-for-beginners/unsloth-requirements.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/unsloth"
    }
  ],
  "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": 6,
    "after": [
      "inference.tool-loop"
    ],
    "area": "models",
    "asks": [
      "what does it cost to keep my fine-tune deployed",
      "serve my LoRA per token",
      "can I undeploy it when it's not in use"
    ],
    "before": [
      "fine-tuning.managed-job"
    ],
    "blockers": [
      "hourly hosting fee charged whether or not the model is called",
      "deployment deleted after an idle period",
      "redeploy takes minutes, too slow for on-demand use"
    ],
    "capabilities": [
      "finetune.serverless-serve",
      "finetune.lora"
    ],
    "category": "fine-tuning",
    "categoryName": "Fine-tuning",
    "checked": "2026-11-15",
    "companies": {
      "fit": 0,
      "fitWithLimit": 6,
      "tagged": 10
    },
    "competition": "none",
    "fits": null,
    "fitsWithLimit": [
      "amazon-bedrock-customization",
      "azure-foundry-fine-tuning",
      "fireworks-fine-tuning",
      "nebius-token-factory-fine-tuning",
      "together-fine-tuning",
      "vertex-ai-tuning"
    ],
    "id": "fine-tuning.idle-serving-cost",
    "listings": {
      "caveat": 6,
      "no": 2,
      "notRead": 0,
      "tagged": 10,
      "unchecked": 1,
      "yes": 0
    },
    "name": "Keep a rarely used tuned model callable without paying for idle time",
    "status": "draft",
    "success": "The docs state the hourly hosting fee, storage fee and idle-deletion rule for a tuned model, and either offer per-token serving with no idle charge or a deploy that can be scripted and is ready within a stated time.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/fine-tuning.idle-serving-cost.json",
    "weight": 12,
    "weightBasis": "6 of 47 accounts: two Microsoft Q\u0026A threads on Azure hosting fees, a Bedrock imported-model storage issue, a Tinker user for whom the economics failed, and two Together users citing serverless LoRA at the base price"
  }
}
