{
  "@context": "https://schema.org",
  "@type": "Dataset",
  "@id": "https://www.requesty.ai/data/provider-throughput-density-october-2026",
  "id": "provider-throughput-october-2026",
  "slug": "provider-throughput-density-october-2026",
  "title": "Provider throughput density, October 2026",
  "shortTitle": "Throughput density",
  "topic": "latency",
  "abstract": "Which providers emit tokens fastest? In October 2026 Typesafe led at a median 889 output tokens per second of total latency. Parasail was slowest at 28 tokens per second.",
  "whyItMatters": "Tokens per second of wall-clock time is a rough measure of how quickly a provider turns a request into output. It depends on the model mix, so a provider serving small models will look faster.",
  "questions": [
    "Which AI provider has the highest tokens per second?",
    "How fast do providers generate output tokens?",
    "Which providers are slowest per token?"
  ],
  "period": "Oct 2026",
  "updated": "2026-11-11",
  "license": "CC BY 4.0",
  "licenseUrl": "https://creativecommons.org/licenses/by/4.0/",
  "caveats": [
    "Successful requests with output tokens only. Typesafe serves short, fixed-format completions, which inflates its rate."
  ],
  "keyFindings": [
    "Typesafe: 889 tokens/sec.",
    "DeepSeek: 149 tokens/sec.",
    "Melious: 106 tokens/sec.",
    "Anthropic: 88 tokens/sec."
  ],
  "columns": [
    {
      "key": "provider",
      "label": "Provider",
      "unit": "count"
    },
    {
      "key": "tokens_per_second_p50",
      "label": "p50 tokens / sec",
      "unit": "count"
    },
    {
      "key": "ms_per_token_p50",
      "label": "p50 ms / token",
      "unit": "milliseconds"
    }
  ],
  "rows": [
    {
      "provider": "Vertex (Gemini)",
      "tokens_per_second_p50": 49.2,
      "ms_per_token_p50": 20.3
    },
    {
      "provider": "Azure",
      "tokens_per_second_p50": 68.2,
      "ms_per_token_p50": 14.7
    },
    {
      "provider": "Typesafe",
      "tokens_per_second_p50": 888.9,
      "ms_per_token_p50": 1.1
    },
    {
      "provider": "TensorX",
      "tokens_per_second_p50": 36.6,
      "ms_per_token_p50": 27.3
    },
    {
      "provider": "OpenAI",
      "tokens_per_second_p50": 44.9,
      "ms_per_token_p50": 22.3
    },
    {
      "provider": "DeepInfra",
      "tokens_per_second_p50": 37.1,
      "ms_per_token_p50": 27
    },
    {
      "provider": "Nebius",
      "tokens_per_second_p50": 82.4,
      "ms_per_token_p50": 12.1
    },
    {
      "provider": "Bedrock",
      "tokens_per_second_p50": 51.2,
      "ms_per_token_p50": 19.5
    },
    {
      "provider": "Sference",
      "tokens_per_second_p50": 78.8,
      "ms_per_token_p50": 12.7
    },
    {
      "provider": "Anthropic",
      "tokens_per_second_p50": 87.6,
      "ms_per_token_p50": 11.4
    },
    {
      "provider": "DeepSeek",
      "tokens_per_second_p50": 149.2,
      "ms_per_token_p50": 6.7
    },
    {
      "provider": "Vertex (Claude)",
      "tokens_per_second_p50": 84.2,
      "ms_per_token_p50": 11.9
    },
    {
      "provider": "Novita",
      "tokens_per_second_p50": 30.6,
      "ms_per_token_p50": 32.7
    },
    {
      "provider": "Melious",
      "tokens_per_second_p50": 105.8,
      "ms_per_token_p50": 9.5
    },
    {
      "provider": "Parasail",
      "tokens_per_second_p50": 28.2,
      "ms_per_token_p50": 35.5
    }
  ],
  "rowKey": "provider",
  "citation": {
    "apa": "Requesty (2026). Provider throughput density, October 2026. Requesty Data. https://www.requesty.ai/data/provider-throughput-density-october-2026",
    "bibtex": "@misc{requesty_provider_throughput_density_october_2026,\n  author       = {{Requesty}},\n  title        = {Provider throughput density, October 2026},\n  year         = {2026},\n  howpublished = {\\url{https://www.requesty.ai/data/provider-throughput-density-october-2026}},\n  note         = {Requesty Data}\n}"
  },
  "permalink": "https://www.requesty.ai/data/provider-throughput-density-october-2026",
  "downloads": {
    "json": "https://www.requesty.ai/data/provider-throughput-density-october-2026/data.json",
    "csv": "https://www.requesty.ai/data/provider-throughput-density-october-2026/data.csv",
    "markdown": "https://www.requesty.ai/data/provider-throughput-density-october-2026.md"
  },
  "citedIn": [],
  "image": "https://www.requesty.ai/data/provider-throughput-density-october-2026/opengraph-image",
  "source": {
    "organization": "Requesty",
    "url": "https://www.requesty.ai"
  }
}