{
  "@context": "https://schema.org",
  "@type": "Dataset",
  "@id": "https://requesty.ai/data/operational-metrics-by-provider-april-2026",
  "id": "ops-metrics-april-2026",
  "slug": "operational-metrics-by-provider-april-2026",
  "title": "Operational metrics per provider, April 2026",
  "shortTitle": "Operational metrics",
  "topic": "reliability",
  "abstract": "How reliable is each LLM provider in production? In April 2026 the top eight providers on the Requesty gateway (OpenAI, Anthropic, Vertex (Gemini), Bedrock, DeepSeek, Novita, xAI) sat at 95-99% success rate. Azure trailed at 78%, Vertex (Claude) at 84%, Mistral at 86%, and Moonshot at 6%, a real reliability outlier. Streaming adoption is bimodal too: Azure 68%, Anthropic 57%, everyone else under 30%.",
  "whyItMatters": "Provider success rate translates directly into user-visible failures unless an application has a managed fallback chain. The 95-99% top tier is comfortably reliable; Vertex (Claude) and Azure visibly failing roughly 1 in 5 calls demands either a routing policy or active provider switching at the application layer to avoid sustained user pain.",
  "questions": [
    "Which LLM provider is most reliable in production?",
    "What is the success rate of OpenAI vs Anthropic vs Vertex?",
    "Why do some LLM providers fail more often than others?",
    "How widely is streaming adopted across LLM providers?"
  ],
  "period": "Apr 2026",
  "updated": "2026-05-09",
  "license": "CC BY 4.0",
  "licenseUrl": "https://creativecommons.org/licenses/by/4.0/",
  "caveats": [
    "Apr 2025 success rates are anomalously low (OpenAI 54%, Anthropic 72%) and are likely under-reported because status_code wasn't being captured then. Mar to Apr 2026 success-rate comparisons are reliable; YoY success-rate deltas should be treated softly."
  ],
  "keyFindings": [
    "Success is bimodal: top tier at 95 to 99%, Vertex (Claude) 84%, Azure 78%, Mistral 86%, Moonshot 6%.",
    "Streaming adoption is bimodal: Azure 68% and Anthropic 57%. Vertex (Claude) at 28%. Everyone else <10%.",
    "Cache hit rate ranges from Anthropic-direct 77% to Vertex (Claude) 24% (same model family, 3x spread)."
  ],
  "columns": [
    {
      "key": "provider",
      "label": "Provider",
      "unit": "count"
    },
    {
      "key": "success_rate",
      "label": "Success rate",
      "unit": "percent"
    },
    {
      "key": "streaming_share",
      "label": "Streaming",
      "unit": "percent"
    },
    {
      "key": "cache_hit_rate",
      "label": "Cache hit",
      "unit": "percent"
    }
  ],
  "rows": [
    {
      "provider": "xAI",
      "success_rate": 0.993,
      "streaming_share": 0.013,
      "cache_hit_rate": 0.357
    },
    {
      "provider": "DeepSeek",
      "success_rate": 0.983,
      "streaming_share": 0.028,
      "cache_hit_rate": 0.483
    },
    {
      "provider": "OpenAI",
      "success_rate": 0.98,
      "streaming_share": 0.072,
      "cache_hit_rate": 0.364
    },
    {
      "provider": "Novita",
      "success_rate": 0.972,
      "streaming_share": 0.023,
      "cache_hit_rate": 0.319
    },
    {
      "provider": "Anthropic",
      "success_rate": 0.96,
      "streaming_share": 0.569,
      "cache_hit_rate": 0.775
    },
    {
      "provider": "Vertex (Gemini)",
      "success_rate": 0.959,
      "streaming_share": 0.037,
      "cache_hit_rate": 0.096
    },
    {
      "provider": "Bedrock",
      "success_rate": 0.956,
      "streaming_share": 0.097,
      "cache_hit_rate": 0.569
    },
    {
      "provider": "Mistral",
      "success_rate": 0.863,
      "streaming_share": 0.08,
      "cache_hit_rate": 0.041
    },
    {
      "provider": "Vertex (Claude)",
      "success_rate": 0.844,
      "streaming_share": 0.276,
      "cache_hit_rate": 0.235
    },
    {
      "provider": "Azure",
      "success_rate": 0.78,
      "streaming_share": 0.683,
      "cache_hit_rate": 0.41
    },
    {
      "provider": "Moonshot",
      "success_rate": 0.062,
      "streaming_share": 0.048,
      "cache_hit_rate": 0.882
    }
  ],
  "rowKey": "provider",
  "citation": {
    "apa": "Requesty (2026). Operational metrics per provider, April 2026. Requesty Data. https://requesty.ai/data/operational-metrics-by-provider-april-2026",
    "bibtex": "@misc{requesty_operational_metrics_by_provider_april_2026,\n  author       = {{Requesty}},\n  title        = {Operational metrics per provider, April 2026},\n  year         = {2026},\n  howpublished = {\\url{https://requesty.ai/data/operational-metrics-by-provider-april-2026}},\n  note         = {Requesty Data}\n}"
  },
  "permalink": "https://requesty.ai/data/operational-metrics-by-provider-april-2026",
  "downloads": {
    "json": "https://requesty.ai/data/operational-metrics-by-provider-april-2026/data.json",
    "csv": "https://requesty.ai/data/operational-metrics-by-provider-april-2026/data.csv",
    "markdown": "https://requesty.ai/data/operational-metrics-by-provider-april-2026.md"
  },
  "citedIn": [
    {
      "title": "What the gateway saw in April 2026",
      "url": "https://requesty.ai/blog/provider-trends-april-2026-agentic-share-latency"
    }
  ],
  "image": "https://requesty.ai/data/operational-metrics-by-provider-april-2026/opengraph-image",
  "source": {
    "organization": "Requesty",
    "url": "https://requesty.ai"
  }
}