{
  "@context": "https://schema.org",
  "@type": "Dataset",
  "@id": "https://www.requesty.ai/data/provider-latency-yoy-october-2026",
  "id": "latency-yoy-october-2026",
  "slug": "provider-latency-yoy-october-2026",
  "title": "p50 latency year over year: October 2025 to October 2026",
  "shortTitle": "Latency YoY",
  "topic": "latency",
  "abstract": "Did AI providers get faster over the past year? Comparing October 2025 with October 2026, Nebius median latency fell 90%, from 2.8s to 288ms. OpenAI rose from 556ms to 2.3s as its traffic shifted to larger reasoning models.",
  "whyItMatters": "Year over year latency changes mix two effects: provider infrastructure and the models customers run. A rise usually means heavier models, not a slower provider.",
  "questions": [
    "Have LLM providers gotten faster in the last year?",
    "Which provider improved latency the most?",
    "Why did some providers get slower?"
  ],
  "period": "Oct 2025 to Oct 2026",
  "updated": "2026-11-11",
  "license": "CC BY 4.0",
  "licenseUrl": "https://creativecommons.org/licenses/by/4.0/",
  "caveats": [
    "Providers with at least 50k requests in both months.",
    "The model mix on each provider changed between the two months."
  ],
  "keyFindings": [
    "Nebius: 2.8s to 288ms (-90%).",
    "Vertex (Gemini): 2.8s to 816ms (-71%).",
    "Vertex (Claude): 6.3s to 2.9s (-54%).",
    "Anthropic: 4.2s to 4.0s (-5%).",
    "Bedrock: 3.9s to 4.3s (+10%).",
    "xAI: 4.2s to 5.0s (+19%).",
    "OpenAI: 556ms to 2.3s (+306%)."
  ],
  "columns": [
    {
      "key": "provider",
      "label": "Provider",
      "unit": "count"
    },
    {
      "key": "prior_ms",
      "label": "Oct 2025 p50",
      "unit": "milliseconds"
    },
    {
      "key": "current_ms",
      "label": "Oct 2026 p50",
      "unit": "milliseconds"
    },
    {
      "key": "delta_pct",
      "label": "YoY delta",
      "unit": "percent"
    }
  ],
  "rows": [
    {
      "provider": "Nebius",
      "prior_ms": 2771,
      "current_ms": 288,
      "delta_pct": -0.8961
    },
    {
      "provider": "Vertex (Gemini)",
      "prior_ms": 2773,
      "current_ms": 816,
      "delta_pct": -0.7056
    },
    {
      "provider": "Vertex (Claude)",
      "prior_ms": 6282,
      "current_ms": 2868,
      "delta_pct": -0.5435
    },
    {
      "provider": "Anthropic",
      "prior_ms": 4213,
      "current_ms": 4016,
      "delta_pct": -0.0468
    },
    {
      "provider": "Bedrock",
      "prior_ms": 3935,
      "current_ms": 4323,
      "delta_pct": 0.0986
    },
    {
      "provider": "xAI",
      "prior_ms": 4194,
      "current_ms": 4971,
      "delta_pct": 0.1853
    },
    {
      "provider": "OpenAI",
      "prior_ms": 556,
      "current_ms": 2255,
      "delta_pct": 3.0581
    }
  ],
  "rowKey": "provider",
  "citation": {
    "apa": "Requesty (2026). p50 latency year over year: October 2025 to October 2026. Requesty Data. https://www.requesty.ai/data/provider-latency-yoy-october-2026",
    "bibtex": "@misc{requesty_provider_latency_yoy_october_2026,\n  author       = {{Requesty}},\n  title        = {p50 latency year over year: October 2025 to October 2026},\n  year         = {2026},\n  howpublished = {\\url{https://www.requesty.ai/data/provider-latency-yoy-october-2026}},\n  note         = {Requesty Data}\n}"
  },
  "permalink": "https://www.requesty.ai/data/provider-latency-yoy-october-2026",
  "downloads": {
    "json": "https://www.requesty.ai/data/provider-latency-yoy-october-2026/data.json",
    "csv": "https://www.requesty.ai/data/provider-latency-yoy-october-2026/data.csv",
    "markdown": "https://www.requesty.ai/data/provider-latency-yoy-october-2026.md"
  },
  "citedIn": [],
  "image": "https://www.requesty.ai/data/provider-latency-yoy-october-2026/opengraph-image",
  "source": {
    "organization": "Requesty",
    "url": "https://www.requesty.ai"
  }
}