{
  "@context": "https://schema.org",
  "@type": "Dataset",
  "@id": "https://requesty.ai/data/finish-reason-mix-by-provider-april-2026",
  "id": "finish-reason-april-2026",
  "slug": "finish-reason-mix-by-provider-april-2026",
  "title": "finish_reason mix per provider, April 2026",
  "shortTitle": "finish_reason mix by provider",
  "topic": "agentic",
  "abstract": "Which AI providers serve the most agentic traffic? In April 2026 Anthropic-direct returned `finish_reason = tool_calls` on 52% of successful completions on the Requesty gateway, about 2× the next provider and 17× higher than OpenAI direct. OpenAI Responses (26%), Vertex (Claude) (23%) and Azure (23%) formed a clear second tier. Splitting Vertex into Gemini and Claude cohorts shows the gap inside that route: Vertex (Claude) 23% vs Vertex (Gemini) 13%.",
  "whyItMatters": "`finish_reason = tool_calls` is the cleanest signal that a model was driving an agent loop rather than answering a chat prompt. Providers cluster into clear agentic and non-agentic tiers, which has direct implications for routing. Sending agent traffic to a non-agentic provider often produces shorter context windows and worse tool-following without users realising why their agent feels \"dumber\".",
  "questions": [
    "Which LLM provider is best for agentic workloads?",
    "What share of LLM traffic uses tool calls in 2026?",
    "Which AI providers are best for AI agents?",
    "Why does Anthropic dominate agent traffic vs OpenAI?"
  ],
  "period": "Apr 2026",
  "updated": "2026-05-09",
  "license": "CC BY 4.0",
  "licenseUrl": "https://creativecommons.org/licenses/by/4.0/",
  "caveats": [
    "Apr 2026 only. finish_reason was not populated for any 2025 row.",
    "Moonshot 94% blank/error is a reliability problem, not a labeling artefact (success rate 6.2%)."
  ],
  "keyFindings": [
    "Anthropic-direct: 52% tool_calls, the highest agentic share on the platform.",
    "OpenAI Responses (26%), Vertex (Claude) (23%) and Azure (23%) form a clear second tier.",
    "Vertex (Claude) at 23% versus Vertex (Gemini) at 13%: same provider routing, different workload by an order of magnitude.",
    "OpenAI direct is at 3% tool_calls, 17× lower than Anthropic-direct.",
    "Bedrock Claude (7%) versus Anthropic-direct Claude (52%): same model, very different workload mix.",
    "NULL finish_reason correlates with successful=false. Moonshot 94% blank is a reliability outlier on that route."
  ],
  "columns": [
    {
      "key": "provider",
      "label": "Provider",
      "unit": "count",
      "description": "provider_used tag from the gateway log"
    },
    {
      "key": "tool_calls",
      "label": "tool_calls",
      "unit": "percent",
      "description": "Share of provider's own successful completions"
    },
    {
      "key": "stop",
      "label": "stop",
      "unit": "percent"
    },
    {
      "key": "length",
      "label": "length",
      "unit": "percent"
    },
    {
      "key": "blank_or_error",
      "label": "blank/error",
      "unit": "percent"
    }
  ],
  "rows": [
    {
      "provider": "Anthropic",
      "tool_calls": 0.522,
      "stop": 0.426,
      "length": 0.014,
      "blank_or_error": 0.038
    },
    {
      "provider": "OpenAI Responses",
      "tool_calls": 0.259,
      "stop": 0.71,
      "length": 0.01,
      "blank_or_error": 0.021
    },
    {
      "provider": "Vertex (Claude)",
      "tool_calls": 0.234,
      "stop": 0.562,
      "length": 0.053,
      "blank_or_error": 0.151
    },
    {
      "provider": "Azure",
      "tool_calls": 0.226,
      "stop": 0.575,
      "length": 0.004,
      "blank_or_error": 0.195
    },
    {
      "provider": "Vertex (Gemini)",
      "tool_calls": 0.135,
      "stop": 0.79,
      "length": 0.033,
      "blank_or_error": 0.042
    },
    {
      "provider": "Bedrock",
      "tool_calls": 0.067,
      "stop": 0.885,
      "length": 0.005,
      "blank_or_error": 0.043
    },
    {
      "provider": "Moonshot",
      "tool_calls": 0.046,
      "stop": 0.014,
      "length": 0.001,
      "blank_or_error": 0.939
    },
    {
      "provider": "OpenAI",
      "tool_calls": 0.033,
      "stop": 0.942,
      "length": 0.006,
      "blank_or_error": 0.019
    },
    {
      "provider": "xAI",
      "tool_calls": 0.029,
      "stop": 0.962,
      "length": 0.002,
      "blank_or_error": 0.007
    },
    {
      "provider": "DeepSeek",
      "tool_calls": 0.015,
      "stop": 0.945,
      "length": 0.022,
      "blank_or_error": 0.018
    }
  ],
  "rowKey": "provider",
  "citation": {
    "apa": "Requesty (2026). finish_reason mix per provider, April 2026. Requesty Data. https://requesty.ai/data/finish-reason-mix-by-provider-april-2026",
    "bibtex": "@misc{requesty_finish_reason_mix_by_provider_april_2026,\n  author       = {{Requesty}},\n  title        = {finish\\_reason mix per provider, April 2026},\n  year         = {2026},\n  howpublished = {\\url{https://requesty.ai/data/finish-reason-mix-by-provider-april-2026}},\n  note         = {Requesty Data}\n}"
  },
  "permalink": "https://requesty.ai/data/finish-reason-mix-by-provider-april-2026",
  "downloads": {
    "json": "https://requesty.ai/data/finish-reason-mix-by-provider-april-2026/data.json",
    "csv": "https://requesty.ai/data/finish-reason-mix-by-provider-april-2026/data.csv",
    "markdown": "https://requesty.ai/data/finish-reason-mix-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/finish-reason-mix-by-provider-april-2026/opengraph-image",
  "source": {
    "organization": "Requesty",
    "url": "https://requesty.ai"
  }
}