{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/fine-tuning.idle-serving-cost/",
    "json": "https://www.anchorterminal.com/niches/fine-tuning.idle-serving-cost/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/fine-tuning.idle-serving-cost/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/fine-tuning.idle-serving-cost/index.min.md"
  },
  "markdown": "No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 0 | 6 | 10 | 12 | 6 |\n\n## What counts as done\n\nThe 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.\n\nHow agents ask for it: 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\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Amazon Bedrock model customisation (Amazon Web Services, Inc.)**: 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.\n- **Microsoft Foundry fine-tuning (Azure OpenAI) (Microsoft Corporation)**: 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.\n- **Fireworks AI Fine-tuning (Fireworks.ai, Inc.)**: 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.\n- **Nebius Token Factory fine-tuning (Nebius B.V.)**: 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.\n- **Together AI Fine-tuning (Together Computer, Inc.)**: 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.\n- **Vertex AI Gemini tuning (Google LLC)**: 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.\n\n## Couldn't check\n\nThe docs were closed to us, or silent. These carry no mark either way.\n\n- **Tinker (Thinking Machines Labs, Inc.)**: Sampling and checkpoint storage prices are on the docs site, which was not read because the Service Terms bar automated scraping of the documentation.\n\n- not this job: Axolotl (Axolotl AI): Not a hosting service.\n- not this job: Unsloth (Unsloth): Not a hosting service; serving cost depends on wherever the export runs.\n\n## What stops agents finishing\n\n- hourly hosting fee charged whether or not the model is called\n- deployment deleted after an idle period\n- redeploy takes minutes, too slow for on-demand use\n\n## Around it\n\nBefore: fine-tuning.managed-job. After: inference.tool-loop.\n\n## Where this comes from\n\nWeight 12 of 100 in Fine-tuning: 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\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/fine-tuning.idle-serving-cost.json, or the MCP tool get_use_case with id fine-tuning.idle-serving-cost. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "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"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Keep a rarely used tuned model callable without paying for idle time",
        "url": ""
      }
    ],
    "description": "Keep a rarely used tuned model callable without paying for idle time: 0 companies fully do it, 6 with a limit, 10 carry the tag. Every listing in Fine-tuning with the reason and a source.",
    "facts": null,
    "h1": "Keep a rarely used tuned model callable without paying for idle time",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/fine-tuning.idle-serving-cost/",
    "published": "",
    "section": "agents",
    "title": "Keep a rarely used tuned model callable without paying for idle time…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/fine-tuning.idle-serving-cost/"
  },
  "tokens": {
    "markdown": 1100,
    "slim": 330
  },
  "version": 1
}
