InferenceX
EN

公开数据 API

InferenceX API 参考文档

从 InferenceX 使用的同一组数据源中，读取基准测试数据、溯源信息、数据集、CollectiveX 数据和诊断数据。

机器可读契约

OpenAPI 3.1 JSON

查看标准 schema，或直接将其传入工具链。

打开 OpenAPI JSON
规范版本
v1 · OpenAPI 3.1
身份验证
身份验证已发布的只读端点不需要身份验证。
响应格式
响应格式除非端点明确说明 CSV，否则响应均为 JSON。日期使用 YYYY-MM-DD，时间戳使用 UTC ISO 8601。
基础 URL
https://inferencex.semianalysis.com

01 / 快速入门

快速入门

只需几步，即可从查看契约到获得真实响应。

  1. 01

    查询可用配置

    先查询 availability，选择实际可用的模型、硬件、框架和序列取值。

    查询可用配置
    curl "https://inferencex.semianalysis.com/api/v1/availability"
  2. 02

    获取基准行

    然后为受支持的展示模型请求最新原始基准行。

    获取基准行
    curl "https://inferencex.semianalysis.com/api/v1/benchmarks?model=DeepSeek-R1-0528"

02 / 约定

约定

适用于受支持接口的通用请求、错误与缓存行为。

错误
JSON 错误包含 error 字符串。400 表示参数缺失或无效，404 表示请求的记录不存在，500 表示服务器查询失败。
缓存
只读端点可能由共享缓存提供。CollectiveX 使用较短的刷新窗口，框架版本使用一小时共享缓存。
标识符
基准结果 ID 和 GitHub 运行 ID 为正整数。批量诊断端点接受以逗号分隔并去重的 ID。

03 / 数据结构

BenchmarkRow 与指标

理解主要基准测试响应数据及其中的实测字段。

BenchmarkRow

配置字段与 metrics 映射位于同一层级。metrics 的键可独立扩展，各项指标值均为数字；时间指标以秒为单位。除非指标名另有说明，吞吐量指标均以 token/s/GPU 为单位。

结构

代码
BenchmarkRows

示例

代码
{
  "id": 421,
  "hardware": "h200_sxm",
  "framework": "vllm",
  "model": "dsr1",
  "precision": "fp8",
  "spec_method": "none",
  "disagg": false,
  "is_multinode": false,
  "prefill_tp": 8,
  "prefill_ep": 1,
  "prefill_dp_attention": false,
  "prefill_num_workers": 1,
  "decode_tp": 8,
  "decode_ep": 1,
  "decode_dp_attention": false,
  "decode_num_workers": 1,
  "num_prefill_gpu": 0,
  "num_decode_gpu": 8,
  "benchmark_type": "single_turn",
  "isl": 1024,
  "osl": 1024,
  "conc": 32,
  "offload_mode": "off",
  "image": "vllm/vllm-openai:v0.10.2",
  "recipe_fingerprint": "7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d",
  "metrics": {
    "median_ttft": 0.42,
    "median_tpot": 0.018,
    "tput_per_gpu": 128.4,
    "power_valid": 1,
    "power_metric_schema_version": 2,
    "avg_power_w": 678.5,
    "joules_per_output_token": 5.3,
    "joules_per_total_token": 2.65,
    "avg_temp_c": 61.2
  },
  "date": "2026-08-08",
  "run_url": "https://github.com/semianalysis/inference-benchmarks/actions/runs/123456789"
}

滚动查看完整示例。

实测功率

基准测试数据行可能包含实测功率、能耗和 GPU 遥测指标（avg_power_w、joules_per_*、avg_temp_c、peak_temp_c、avg_util_pct、avg_mem_used_mb）。power_valid 有三种状态：1 表示测量窗口已通过验证；0 表示验证失败，生产端会移除实测值，摄取端也会再次清除，若仍有残留，应视为不可靠；缺失表示该数据行早于验证机制。power_metric_schema_version == 2 规定所有无前缀的 joules_per_* 字段均按整个部署统计能耗。未标注版本的分离式部署数据中，这些字段曾记录单个角色的能耗，因此其统计口径不明确。多节点和分离式运行中，各 worker 的功率和遥测明细位于 workers[]。power_invalid_reasons 与 power_audit 可包含生产端的验证详情。查询实测功率时，使用 powerValid=strictV2，仅保留 power_valid == 1 且 power_metric_schema_version == 2 的行。这是唯一支持的功率筛选值。常规基准测试请求应省略 powerValid，以保留缺少有效功率测量的结果。

结构

代码
BenchmarkRows

示例

代码
{
  "power_valid": 1,
  "power_metric_schema_version": 2,
  "avg_power_w": 678.5,
  "joules_per_output_token": 5.3
}
以 ID 为键的映射

批量诊断响应是以十进制基准结果 ID 为键的 JSON 对象。缺少某个键表示该 ID 没有可用值。

结构

代码
Record<string, value>

示例

代码
{
  "421": true
}
CollectiveX 版本

CollectiveX 读取需要明确指定受支持的契约版本。受支持版本：1。

结构

代码
CollectiveXDataset

04 / 参考

端点参考

展开任一操作，即可查看参数、状态码和完整示例。

28 项操作

核心基准数据

基准结果、可用配置、工作流来源、评估与可靠性数据。

GET稳定/api/v1/availability列出可用的基准配置

返回已有基准数据的模型、序列、精度、硬件、框架、投机解码方式、基准类型和日期组合。

参数

无需参数。

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/availability'

响应

AvailabilityRows
200

可用配置行。

媒体类型: application/json

响应结构

代码
{
  "type": "array",
  "items": {
    "type": "object",
    "properties": {
      "model": {
        "type": "string"
      },
      "isl": {
        "type": [
          "number",
          "null"
        ]
      },
      "osl": {
        "type": [
          "number",
          "null"
        ]
      },
      "precision": {
        "type": "string"
      },
      "hardware": {
        "type": "string"
      },
      "framework": {
        "type": "string"
      },
      "spec_method": {
        "type": "string"
      },
      "disagg": {
        "type": "boolean"
      },
      "benchmark_type": {
        "type": "string"
      },
      "date": {
        "type": "string",
        "format": "date"
      }
    },
    "required": [
      "model",
      "isl",
      "osl",
      "precision",
      "hardware",
      "framework",
      "spec_method",
      "disagg",
      "benchmark_type",
      "date"
    ],
    "additionalProperties": false
  }
}

滚动查看完整示例。

响应示例

代码
[
  {
    "model": "dsr1",
    "isl": 1024,
    "osl": 1024,
    "precision": "fp8",
    "hardware": "h200_sxm",
    "framework": "vllm",
    "spec_method": "none",
    "disagg": false,
    "benchmark_type": "single_turn",
    "date": "2026-08-08"
  }
]

滚动查看完整示例。

500

可用配置查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET稳定/api/v1/benchmarks读取基准结果

返回指定展示模型的原始基准测试数据行。使用 date 可获取截至指定日期的快照；exact=true 仅返回该日期的数据；runId 用于限定最新结果的查询范围；将 exactRun=true 与数值型 runId 搭配使用，则只返回该工作流运行的数据。view=calculator 返回页面专用的裁剪投影（会移除实测功率指标和 workers，其允许列表可能变化）。powerValid=strictV2 仅返回采用 schema v2 且功率测量通过验证的数据行，不能与 view=calculator 组合使用。省略 powerValid 则保留常规基准测试结果，不按功率有效性筛选。

参数

GET /api/v1/benchmarks: 参数
名称位置类型要求说明示例
modelquerystring必填展示模型名称。DeepSeek-R1-0528
datequerydate可选YYYY-MM-DD 当日或之前的最新数据，exact 为 true 时仅限当日。2026-08-08
exactqueryboolean可选设为 true 时严格匹配所给日期。false
runIdqueryinteger可选GitHub Actions 数字运行 ID。非数字值会被忽略。123456789
exactRunqueryboolean可选与数字 runId 一起使用时，仅返回该次运行而非截至日期的结果。false
viewqueryenum可选calculator 会将每行裁剪为吞吐量计算器所需的页面专用指标允许列表并移除 workers；此视图不包含实测功率指标。需要同时提供 sequence。省略则返回全部已存储指标，包括实测功率。calculator
sequencequeryenum可选当 view=calculator 时必填，其余情况会被忽略。未知值返回 400 Unknown calculator sequence。1k/1k
powerValidqueryenum可选仅接受 strictV2：保留 metrics.power_valid 为数字 1、且 metrics.power_metric_schema_version 为数字 2 的数据行，其能耗指标采用整个部署的统计口径。省略此参数则不按功率筛选，即使功率缺失或无效，也会保留吞吐量和延迟结果。其他取值（包括空值）返回 400 Unknown powerValid filter。不能与 view=calculator 组合使用。strictV2

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/benchmarks?model=DeepSeek-R1-0528'

响应

BenchmarkRows
200

基准行，标量指标位于 metrics 对象中。

媒体类型: application/json

响应结构

代码
{
  "type": "array",
  "items": {
    "type": "object",
    "properties": {
      "id": {
        "type": "integer"
      },
      "hardware": {
        "type": "string"
      },
      "framework": {
        "type": "string"
      },
      "model": {
        "type": "string"
      },
      "precision": {
        "type": "string"
      },
      "spec_method": {
        "type": "string"
      },
      "disagg": {
        "type": "boolean"
      },
      "is_multinode": {
        "type": "boolean"
      },
      "prefill_tp": {
        "type": "integer"
      },
      "prefill_ep": {
        "type": "integer"
      },
      "prefill_dp_attention": {
        "type": "boolean"
      },
      "prefill_num_workers": {
        "type": "integer"
      },
      "decode_tp": {
        "type": "integer"
      },
      "decode_ep": {
        "type": "integer"
      },
      "decode_dp_attention": {
        "type": "boolean"
      },
      "decode_num_workers": {
        "type": "integer"
      },
      "num_prefill_gpu": {
        "type": "integer"
      },
      "num_decode_gpu": {
        "type": "integer"
      },
      "benchmark_type": {
        "type": "string"
      },
      "isl": {
        "type": [
          "number",
          "null"
        ]
      },
      "osl": {
        "type": [
          "number",
          "null"
        ]
      },
      "conc": {
        "type": "integer"
      },
      "offload_mode": {
        "type": "string"
      },
      "image": {
        "type": [
          "string",
          "null"
        ]
      },
      "recipe_fingerprint": {
        "type": [
          "string",
          "null"
        ]
      },
      "metrics": {
        "type": "object",
        "additionalProperties": {
          "type": "number"
        },
        "description": "Scalar metric map. Keys evolve independently; measured power / energy / GPU-telemetry keys are typed below.",
        "properties": {
          "power_valid": {
            "type": "number",
            "description": "Publication verdict: 1 = validated measurement window; 0 = failed validation — measured power/energy values are withheld from this row end-to-end, so treat any that remain as unreliable; absent = legacy row predating validation."
          },
          "power_metric_schema_version": {
            "type": "number",
            "description": "Power schema version. Version 2 defines every unprefixed joules_per_* field as whole-deployment energy, including on disaggregated runs."
          },
          "avg_power_w": {
            "type": "number",
            "description": "Mean per-GPU power draw in watts during the measured load window."
          },
          "joules_per_successful_query": {
            "type": "number",
            "description": "Whole-deployment energy in joules divided by successful requests."
          },
          "joules_per_output_token": {
            "type": "number",
            "description": "Energy per generated output token in joules; cluster-wide on schema-version-2 rows, including disaggregated runs."
          },
          "joules_per_total_token": {
            "type": "number",
            "description": "Total system energy divided by input plus output tokens; a workload-shape-fair view that does not treat prompt tokens as free."
          },
          "prefill_avg_power_w": {
            "type": "number",
            "description": "Mean per-GPU power draw in watts across prefill workers; emitted only for deployments with distinct prefill and decode roles."
          },
          "decode_avg_power_w": {
            "type": "number",
            "description": "Mean per-GPU power draw in watts across decode workers; emitted only for deployments with distinct prefill and decode roles."
          },
          "joules_per_input_token": {
            "type": "number",
            "description": "Energy per input token in joules; cluster-wide on schema-version-2 rows."
          },
          "prefill_joules_per_input_token": {
            "type": "number",
            "description": "Role-local prefill energy per input token in joules."
          },
          "decode_joules_per_output_token": {
            "type": "number",
            "description": "Role-local decode energy per generated output token in joules."
          },
          "avg_temp_c": {
            "type": "number",
            "description": "Mean per-GPU temperature in degrees Celsius during the load window."
          },
          "peak_temp_c": {
            "type": "number",
            "description": "Maximum instantaneous per-GPU temperature in degrees Celsius during the load window."
          },
          "avg_util_pct": {
            "type": "number",
            "description": "Mean per-GPU utilization percentage (0-100) during the load window."
          },
          "avg_mem_used_mb": {
            "type": "number",
            "description": "Mean per-GPU memory used in MB during the load window."
          }
        }
      },
      "workers": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "role": {
              "type": "string"
            },
            "worker_idx": {
              "type": "integer"
            },
            "hosts": {
              "type": "array",
              "items": {
                "type": "string"
              }
            },
            "num_gpus": {
              "type": "integer"
            },
            "avg_power_w": {
              "type": "number"
            },
            "avg_temp_c": {
              "type": "number"
            },
            "peak_temp_c": {
              "type": "number"
            },
            "avg_util_pct": {
              "type": "number"
            },
            "avg_mem_used_mb": {
              "type": "number"
            }
          },
          "required": [
            "role",
            "worker_idx",
            "num_gpus",
            "avg_power_w"
          ],
          "additionalProperties": false
        }
      },
      "power_invalid_reasons": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Optional snake_case validation reason codes when metrics.power_valid == 0. Absent on legacy rows."
      },
      "power_audit": {
        "type": "object",
        "properties": {
          "window_start_unix": {
            "type": "number"
          },
          "window_end_unix": {
            "type": "number"
          },
          "expected_gpu_count": {
            "type": "integer"
          },
          "observed_gpu_count": {
            "type": "integer"
          },
          "sample_count": {
            "type": "integer"
          },
          "max_sample_gap_s": {
            "type": "number"
          },
          "producer_sha": {
            "type": [
              "string",
              "null"
            ]
          },
          "exporter_image_sha256": {
            "type": [
              "string",
              "null"
            ]
          }
        },
        "additionalProperties": true,
        "description": "Optional power measurement-window audit. Individual fields may be absent; legacy rows omit the object."
      },
      "date": {
        "type": "string",
        "format": "date"
      },
      "workflow_run_id": {
        "type": "integer"
      },
      "run_started_at": {
        "type": [
          "string",
          "null"
        ],
        "format": "date-time"
      },
      "run_url": {
        "type": [
          "string",
          "null"
        ]
      }
    },
    "required": [
      "id",
      "hardware",
      "framework",
      "model",
      "precision",
      "spec_method",
      "disagg",
      "is_multinode",
      "prefill_tp",
      "prefill_ep",
      "prefill_dp_attention",
      "prefill_num_workers",
      "decode_tp",
      "decode_ep",
      "decode_dp_attention",
      "decode_num_workers",
      "num_prefill_gpu",
      "num_decode_gpu",
      "benchmark_type",
      "isl",
      "osl",
      "conc",
      "offload_mode",
      "image",
      "recipe_fingerprint",
      "metrics",
      "date",
      "run_url"
    ],
    "additionalProperties": false
  }
}

滚动查看完整示例。

响应示例

代码
[
  {
    "id": 421,
    "hardware": "h200_sxm",
    "framework": "vllm",
    "model": "dsr1",
    "precision": "fp8",
    "spec_method": "none",
    "disagg": false,
    "is_multinode": false,
    "prefill_tp": 8,
    "prefill_ep": 1,
    "prefill_dp_attention": false,
    "prefill_num_workers": 1,
    "decode_tp": 8,
    "decode_ep": 1,
    "decode_dp_attention": false,
    "decode_num_workers": 1,
    "num_prefill_gpu": 0,
    "num_decode_gpu": 8,
    "benchmark_type": "single_turn",
    "isl": 1024,
    "osl": 1024,
    "conc": 32,
    "offload_mode": "off",
    "image": "vllm/vllm-openai:v0.10.2",
    "recipe_fingerprint": "7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d",
    "metrics": {
      "median_ttft": 0.42,
      "median_tpot": 0.018,
      "tput_per_gpu": 128.4,
      "power_valid": 1,
      "power_metric_schema_version": 2,
      "avg_power_w": 678.5,
      "joules_per_output_token": 5.3,
      "joules_per_total_token": 2.65,
      "avg_temp_c": 61.2
    },
    "date": "2026-08-08",
    "run_url": "https://github.com/semianalysis/inference-benchmarks/actions/runs/123456789"
  }
]

滚动查看完整示例。

400

模型缺失或不受支持、计算器序列未知、提供的 powerValid 取值不是 strictV2，或 powerValid=strictV2 与 view=calculator 组合使用。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Unknown model"
}
500

基准查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET稳定/api/v1/benchmarks/history读取基准历史

返回指定模型在固定输入/输出 token 组合或 Agentic Traces 条件下的全部历史基准测试数据行。

参数

GET /api/v1/benchmarks/history: 参数
名称位置类型要求说明示例
modelquerystring必填展示模型名称。DeepSeek-R1-0528
islqueryinteger可选正整数输入序列长度，单位为 token；除非 benchmarkType=agentic_traces，否则必填。1024
oslqueryinteger可选正整数输出序列长度，单位为 token；除非 benchmarkType=agentic_traces，否则必填。1024
benchmarkTypequerystring可选设为 agentic_traces 可在不提供 ISL/OSL 的情况下读取 Agentic Traces 历史。agentic_traces
viewqueryenum可选calculator 会将每行裁剪为吞吐量计算器所需的指标，以减小响应体积。省略则返回全部已存储指标，包括实测功率。calculator

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/benchmarks/history?model=DeepSeek-R1-0528&isl=1024&osl=1024'

响应

BenchmarkRows
200

历史基准行。

媒体类型: application/json

响应结构

代码
{
  "type": "array",
  "items": {
    "type": "object",
    "properties": {
      "id": {
        "type": "integer"
      },
      "hardware": {
        "type": "string"
      },
      "framework": {
        "type": "string"
      },
      "model": {
        "type": "string"
      },
      "precision": {
        "type": "string"
      },
      "spec_method": {
        "type": "string"
      },
      "disagg": {
        "type": "boolean"
      },
      "is_multinode": {
        "type": "boolean"
      },
      "prefill_tp": {
        "type": "integer"
      },
      "prefill_ep": {
        "type": "integer"
      },
      "prefill_dp_attention": {
        "type": "boolean"
      },
      "prefill_num_workers": {
        "type": "integer"
      },
      "decode_tp": {
        "type": "integer"
      },
      "decode_ep": {
        "type": "integer"
      },
      "decode_dp_attention": {
        "type": "boolean"
      },
      "decode_num_workers": {
        "type": "integer"
      },
      "num_prefill_gpu": {
        "type": "integer"
      },
      "num_decode_gpu": {
        "type": "integer"
      },
      "benchmark_type": {
        "type": "string"
      },
      "isl": {
        "type": [
          "number",
          "null"
        ]
      },
      "osl": {
        "type": [
          "number",
          "null"
        ]
      },
      "conc": {
        "type": "integer"
      },
      "offload_mode": {
        "type": "string"
      },
      "image": {
        "type": [
          "string",
          "null"
        ]
      },
      "recipe_fingerprint": {
        "type": [
          "string",
          "null"
        ]
      },
      "metrics": {
        "type": "object",
        "additionalProperties": {
          "type": "number"
        },
        "description": "Scalar metric map. Keys evolve independently; measured power / energy / GPU-telemetry keys are typed below.",
        "properties": {
          "power_valid": {
            "type": "number",
            "description": "Publication verdict: 1 = validated measurement window; 0 = failed validation — measured power/energy values are withheld from this row end-to-end, so treat any that remain as unreliable; absent = legacy row predating validation."
          },
          "power_metric_schema_version": {
            "type": "number",
            "description": "Power schema version. Version 2 defines every unprefixed joules_per_* field as whole-deployment energy, including on disaggregated runs."
          },
          "avg_power_w": {
            "type": "number",
            "description": "Mean per-GPU power draw in watts during the measured load window."
          },
          "joules_per_successful_query": {
            "type": "number",
            "description": "Whole-deployment energy in joules divided by successful requests."
          },
          "joules_per_output_token": {
            "type": "number",
            "description": "Energy per generated output token in joules; cluster-wide on schema-version-2 rows, including disaggregated runs."
          },
          "joules_per_total_token": {
            "type": "number",
            "description": "Total system energy divided by input plus output tokens; a workload-shape-fair view that does not treat prompt tokens as free."
          },
          "prefill_avg_power_w": {
            "type": "number",
            "description": "Mean per-GPU power draw in watts across prefill workers; emitted only for deployments with distinct prefill and decode roles."
          },
          "decode_avg_power_w": {
            "type": "number",
            "description": "Mean per-GPU power draw in watts across decode workers; emitted only for deployments with distinct prefill and decode roles."
          },
          "joules_per_input_token": {
            "type": "number",
            "description": "Energy per input token in joules; cluster-wide on schema-version-2 rows."
          },
          "prefill_joules_per_input_token": {
            "type": "number",
            "description": "Role-local prefill energy per input token in joules."
          },
          "decode_joules_per_output_token": {
            "type": "number",
            "description": "Role-local decode energy per generated output token in joules."
          },
          "avg_temp_c": {
            "type": "number",
            "description": "Mean per-GPU temperature in degrees Celsius during the load window."
          },
          "peak_temp_c": {
            "type": "number",
            "description": "Maximum instantaneous per-GPU temperature in degrees Celsius during the load window."
          },
          "avg_util_pct": {
            "type": "number",
            "description": "Mean per-GPU utilization percentage (0-100) during the load window."
          },
          "avg_mem_used_mb": {
            "type": "number",
            "description": "Mean per-GPU memory used in MB during the load window."
          }
        }
      },
      "workers": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "role": {
              "type": "string"
            },
            "worker_idx": {
              "type": "integer"
            },
            "hosts": {
              "type": "array",
              "items": {
                "type": "string"
              }
            },
            "num_gpus": {
              "type": "integer"
            },
            "avg_power_w": {
              "type": "number"
            },
            "avg_temp_c": {
              "type": "number"
            },
            "peak_temp_c": {
              "type": "number"
            },
            "avg_util_pct": {
              "type": "number"
            },
            "avg_mem_used_mb": {
              "type": "number"
            }
          },
          "required": [
            "role",
            "worker_idx",
            "num_gpus",
            "avg_power_w"
          ],
          "additionalProperties": false
        }
      },
      "power_invalid_reasons": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Optional snake_case validation reason codes when metrics.power_valid == 0. Absent on legacy rows."
      },
      "power_audit": {
        "type": "object",
        "properties": {
          "window_start_unix": {
            "type": "number"
          },
          "window_end_unix": {
            "type": "number"
          },
          "expected_gpu_count": {
            "type": "integer"
          },
          "observed_gpu_count": {
            "type": "integer"
          },
          "sample_count": {
            "type": "integer"
          },
          "max_sample_gap_s": {
            "type": "number"
          },
          "producer_sha": {
            "type": [
              "string",
              "null"
            ]
          },
          "exporter_image_sha256": {
            "type": [
              "string",
              "null"
            ]
          }
        },
        "additionalProperties": true,
        "description": "Optional power measurement-window audit. Individual fields may be absent; legacy rows omit the object."
      },
      "date": {
        "type": "string",
        "format": "date"
      },
      "workflow_run_id": {
        "type": "integer"
      },
      "run_started_at": {
        "type": [
          "string",
          "null"
        ],
        "format": "date-time"
      },
      "run_url": {
        "type": [
          "string",
          "null"
        ]
      }
    },
    "required": [
      "id",
      "hardware",
      "framework",
      "model",
      "precision",
      "spec_method",
      "disagg",
      "is_multinode",
      "prefill_tp",
      "prefill_ep",
      "prefill_dp_attention",
      "prefill_num_workers",
      "decode_tp",
      "decode_ep",
      "decode_dp_attention",
      "decode_num_workers",
      "num_prefill_gpu",
      "num_decode_gpu",
      "benchmark_type",
      "isl",
      "osl",
      "conc",
      "offload_mode",
      "image",
      "recipe_fingerprint",
      "metrics",
      "date",
      "run_url"
    ],
    "additionalProperties": false
  }
}

滚动查看完整示例。

响应示例

代码
[
  {
    "id": 421,
    "hardware": "h200_sxm",
    "framework": "vllm",
    "model": "dsr1",
    "precision": "fp8",
    "spec_method": "none",
    "disagg": false,
    "is_multinode": false,
    "prefill_tp": 8,
    "prefill_ep": 1,
    "prefill_dp_attention": false,
    "prefill_num_workers": 1,
    "decode_tp": 8,
    "decode_ep": 1,
    "decode_dp_attention": false,
    "decode_num_workers": 1,
    "num_prefill_gpu": 0,
    "num_decode_gpu": 8,
    "benchmark_type": "single_turn",
    "isl": 1024,
    "osl": 1024,
    "conc": 32,
    "offload_mode": "off",
    "image": "vllm/vllm-openai:v0.10.2",
    "recipe_fingerprint": "7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d7d72a33d",
    "metrics": {
      "median_ttft": 0.42,
      "median_tpot": 0.018,
      "tput_per_gpu": 128.4,
      "power_valid": 1,
      "power_metric_schema_version": 2,
      "avg_power_w": 678.5,
      "joules_per_output_token": 5.3,
      "joules_per_total_token": 2.65,
      "avg_temp_c": 61.2
    },
    "date": "2026-08-08",
    "run_url": "https://github.com/semianalysis/inference-benchmarks/actions/runs/123456789"
  }
]

滚动查看完整示例。

400

必填参数缺失或模型不受支持。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "model, isl, and osl are required"
}
500

历史查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET稳定/api/v1/workflow-info读取工作流溯源信息

返回工作流运行、变更记录、可用配置，以及各次运行涵盖的配置。省略 date 时返回所有日期的数据。

参数

GET /api/v1/workflow-info: 参数
名称位置类型要求说明示例
datequerydate可选可选的 YYYY-MM-DD 筛选条件。2026-08-08
benchmarkTypequerystring可选设为 agentic_traces 可将每次运行的配置覆盖限定为 Agentic Traces。agentic_traces

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/workflow-info?date=2026-08-08'

响应

WorkflowInfo
200

工作流溯源信息，分为四个数组。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "runs": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "github_run_id": {
            "type": "integer"
          },
          "name": {
            "type": "string"
          },
          "conclusion": {
            "type": [
              "string",
              "null"
            ]
          },
          "run_attempt": {
            "type": "integer"
          },
          "html_url": {
            "type": [
              "string",
              "null"
            ]
          },
          "created_at": {
            "type": "string",
            "format": "date-time"
          },
          "date": {
            "type": "string",
            "format": "date"
          }
        },
        "required": [
          "github_run_id",
          "name",
          "conclusion",
          "run_attempt",
          "html_url",
          "created_at",
          "date"
        ],
        "additionalProperties": false
      }
    },
    "changelogs": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "configs": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "runConfigs": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    }
  },
  "required": [
    "runs",
    "changelogs",
    "configs",
    "runConfigs"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "runs": [
    {
      "github_run_id": 123456789,
      "name": "nightly-h200",
      "conclusion": "success",
      "run_attempt": 1,
      "html_url": "https://github.com/semianalysis/inference-benchmarks/actions/runs/123456789",
      "created_at": "2026-08-08T03:00:00Z",
      "date": "2026-08-08"
    }
  ],
  "changelogs": [],
  "configs": [],
  "runConfigs": []
}

滚动查看完整示例。

400

date 不是 YYYY-MM-DD。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Invalid date format (YYYY-MM-DD required)"
}
500

工作流查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET稳定/api/v1/evaluations列出评估汇总

返回最新尝试的评估结果，包含配置、任务、来源和指标值。

参数

无需参数。

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/evaluations'

响应

EvaluationRows
200

评估结果行。

媒体类型: application/json

响应结构

代码
{
  "type": "array",
  "items": {
    "type": "object",
    "properties": {
      "id": {
        "type": "integer"
      },
      "config_id": {
        "type": "integer"
      },
      "hardware": {
        "type": "string"
      },
      "framework": {
        "type": "string"
      },
      "model": {
        "type": "string"
      },
      "precision": {
        "type": "string"
      },
      "spec_method": {
        "type": "string"
      },
      "disagg": {
        "type": "boolean"
      },
      "is_multinode": {
        "type": "boolean"
      },
      "prefill_tp": {
        "type": "integer"
      },
      "prefill_ep": {
        "type": "integer"
      },
      "prefill_dp_attention": {
        "type": "boolean"
      },
      "prefill_num_workers": {
        "type": "integer"
      },
      "decode_tp": {
        "type": "integer"
      },
      "decode_ep": {
        "type": "integer"
      },
      "decode_dp_attention": {
        "type": "boolean"
      },
      "decode_num_workers": {
        "type": "integer"
      },
      "num_prefill_gpu": {
        "type": "integer"
      },
      "num_decode_gpu": {
        "type": "integer"
      },
      "task": {
        "type": "string"
      },
      "date": {
        "type": "string",
        "format": "date"
      },
      "conc": {
        "type": [
          "number",
          "null"
        ]
      },
      "metrics": {
        "type": "object",
        "additionalProperties": {
          "type": "number"
        }
      },
      "timestamp": {
        "type": "string",
        "format": "date-time"
      },
      "run_url": {
        "type": [
          "string",
          "null"
        ]
      }
    },
    "required": [
      "id",
      "config_id",
      "hardware",
      "framework",
      "model",
      "precision",
      "spec_method",
      "disagg",
      "is_multinode",
      "prefill_tp",
      "prefill_ep",
      "prefill_dp_attention",
      "prefill_num_workers",
      "decode_tp",
      "decode_ep",
      "decode_dp_attention",
      "decode_num_workers",
      "num_prefill_gpu",
      "num_decode_gpu",
      "task",
      "date",
      "conc",
      "metrics",
      "timestamp",
      "run_url"
    ],
    "additionalProperties": false
  }
}

滚动查看完整示例。

响应示例

代码
[
  {
    "id": 72,
    "config_id": 11,
    "hardware": "h200_sxm",
    "framework": "vllm",
    "model": "dsr1",
    "precision": "fp8",
    "spec_method": "none",
    "disagg": false,
    "is_multinode": false,
    "prefill_tp": 8,
    "prefill_ep": 1,
    "prefill_dp_attention": false,
    "prefill_num_workers": 1,
    "decode_tp": 8,
    "decode_ep": 1,
    "decode_dp_attention": false,
    "decode_num_workers": 1,
    "num_prefill_gpu": 0,
    "num_decode_gpu": 8,
    "task": "gpqa",
    "date": "2026-08-08",
    "conc": null,
    "metrics": {
      "accuracy": 0.78
    },
    "timestamp": "2026-08-08T03:00:00Z",
    "run_url": null
  }
]

滚动查看完整示例。

500

评估查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET稳定/api/v1/reliability列出基准可靠性

按硬件和日期返回成功运行数与总运行数。

参数

无需参数。

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/reliability'

响应

ReliabilityRows
200

可靠性计数行。

媒体类型: application/json

响应结构

代码
{
  "type": "array",
  "items": {
    "type": "object",
    "properties": {
      "hardware": {
        "type": "string"
      },
      "date": {
        "type": "string",
        "format": "date"
      },
      "n_success": {
        "type": "integer"
      },
      "total": {
        "type": "integer"
      }
    },
    "required": [
      "hardware",
      "date",
      "n_success",
      "total"
    ],
    "additionalProperties": false
  }
}

滚动查看完整示例。

响应示例

代码
[
  {
    "hardware": "h200_sxm",
    "date": "2026-08-08",
    "n_success": 18,
    "total": 20
  }
]
500

可靠性查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}

外部数据源

面向电子表格、版本跟踪、提交记录和运行镜像的稳定数据源。

GET稳定/api/v1/tco-feed计算 TCO 数据源

为电子表格中的 TCO 模型计算帕累托前沿上的吞吐量数据点或加权分数。所有评分假设都编码在 URL 中。CSV 会以扁平表格形式返回当前所选视图中的相同数据。

参数

GET /api/v1/tco-feed: 参数
名称位置类型要求说明示例
modelquerystring可选数据库模型键或展示模型名称。dsv4
workloadsqueryCSV workload list可选以逗号分隔的 <isl>x<osl> token 组合。1024x1024,8192x1024
tiersqueryCSV number list可选正数交互性目标，单位为每用户每秒输出 token。30,50,75,100
datequerydate可选使用 YYYY-MM-DD 当日或之前的数据。省略则使用最新数据。2026-08-08
formatqueryenum可选响应编码。json
viewqueryenum可选points 针对每个硬件、工作负载与档位的组合返回一行；scores 针对每个硬件返回一行。points
weightsqueryCSV number list可选仅用于 scores。每个档位一个非负权重，并归一化为总和 1。0.35,0.4,0.2,0.05
workload_weightsqueryCSV number list可选仅用于 scores。每个工作负载对应一个非负权重；所有权重归一化后总和为 1，默认使用等权重。0.5,0.5
alphaquerynumber可选仅用于 scores。输入 token 价值比，范围为 [0, 10]。0.25

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/tco-feed?model=dsv4&workloads=1024x1024,8192x1024&tiers=30,50,75,100&view=points&format=json'

响应

TcoFeed
200

所选 points 或 scores 视图的响应对象。

媒体类型: application/json

响应结构

代码
{
  "oneOf": [
    {
      "type": "object",
      "properties": {
        "model": {
          "type": "string"
        },
        "db_model_keys": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "date": {
          "type": [
            "string",
            "null"
          ],
          "format": "date"
        },
        "workloads": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "tiers": {
          "type": "array",
          "items": {
            "type": "number"
          }
        },
        "rows": {
          "type": "array",
          "items": {
            "type": "object",
            "additionalProperties": true
          }
        }
      },
      "required": [
        "model",
        "db_model_keys",
        "date",
        "workloads",
        "tiers",
        "rows"
      ],
      "additionalProperties": false
    },
    {
      "type": "object",
      "properties": {
        "model": {
          "type": "string"
        },
        "db_model_keys": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "date": {
          "type": [
            "string",
            "null"
          ],
          "format": "date"
        },
        "workloads": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "tiers": {
          "type": "array",
          "items": {
            "type": "number"
          }
        },
        "weights": {
          "type": "array",
          "items": {
            "type": "number"
          }
        },
        "workload_weights": {
          "type": "array",
          "items": {
            "type": "number"
          }
        },
        "alpha": {
          "type": "number"
        },
        "rows": {
          "type": "array",
          "items": {
            "type": "object",
            "additionalProperties": true
          }
        }
      },
      "required": [
        "model",
        "db_model_keys",
        "date",
        "workloads",
        "tiers",
        "weights",
        "workload_weights",
        "alpha",
        "rows"
      ],
      "additionalProperties": false
    }
  ]
}

滚动查看完整示例。

响应示例

代码
{
  "model": "dsv4",
  "db_model_keys": [
    "dsv4"
  ],
  "date": null,
  "workloads": [
    "1024x1024"
  ],
  "tiers": [
    50
  ],
  "rows": [
    {
      "hardware": "h200_sxm",
      "workload": "1024x1024",
      "tier": 50,
      "tput_per_gpu": 118.2,
      "is_interpolated": true
    }
  ]
}

滚动查看完整示例。

其他表示格式: text/csv

响应结构

代码
{
  "type": "string"
}

响应示例

代码
model,hardware,workload,tier,tput_per_gpu
dsv4,h200_sxm,1024x1024,50,118.2
400

模型、日期、视图、格式、负载、档位、权重或 alpha 值无效。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Invalid tiers: expected comma-separated positive numbers"
}
500

TCO 计算失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET稳定/api/v1/submissions读取提交覆盖

返回配置级提交汇总和每日硬件提交量。

参数

无需参数。

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/submissions'

响应

Submissions
200

提交汇总和数量数组。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "summary": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "model": {
            "type": "string"
          },
          "hardware": {
            "type": "string"
          },
          "framework": {
            "type": "string"
          },
          "precision": {
            "type": "string"
          },
          "spec_method": {
            "type": "string"
          },
          "disagg": {
            "type": "boolean"
          },
          "is_multinode": {
            "type": "boolean"
          },
          "num_prefill_gpu": {
            "type": "integer"
          },
          "num_decode_gpu": {
            "type": "integer"
          },
          "prefill_tp": {
            "type": "integer"
          },
          "prefill_ep": {
            "type": "integer"
          },
          "decode_tp": {
            "type": "integer"
          },
          "decode_ep": {
            "type": "integer"
          },
          "date": {
            "type": "string",
            "format": "date"
          },
          "total_datapoints": {
            "type": "integer"
          },
          "distinct_sequences": {
            "type": "integer"
          },
          "distinct_concurrencies": {
            "type": "integer"
          },
          "max_concurrency": {
            "type": "integer"
          },
          "image": {
            "type": [
              "string",
              "null"
            ]
          }
        },
        "required": [
          "model",
          "hardware",
          "framework",
          "precision",
          "spec_method",
          "disagg",
          "is_multinode",
          "num_prefill_gpu",
          "num_decode_gpu",
          "prefill_tp",
          "prefill_ep",
          "decode_tp",
          "decode_ep",
          "date",
          "total_datapoints",
          "distinct_sequences",
          "distinct_concurrencies",
          "max_concurrency",
          "image"
        ],
        "additionalProperties": false
      }
    },
    "volume": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "date": {
            "type": "string",
            "format": "date"
          },
          "hardware": {
            "type": "string"
          },
          "datapoints": {
            "type": "integer"
          }
        },
        "required": [
          "date",
          "hardware",
          "datapoints"
        ],
        "additionalProperties": false
      }
    }
  },
  "required": [
    "summary",
    "volume"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "summary": [
    {
      "model": "dsr1",
      "hardware": "h200_sxm",
      "framework": "vllm",
      "precision": "fp8",
      "spec_method": "none",
      "disagg": false,
      "is_multinode": false,
      "num_prefill_gpu": 0,
      "num_decode_gpu": 8,
      "prefill_tp": 1,
      "prefill_ep": 1,
      "decode_tp": 8,
      "decode_ep": 1,
      "date": "2026-08-08",
      "total_datapoints": 24,
      "distinct_sequences": 3,
      "distinct_concurrencies": 8,
      "max_concurrency": 256,
      "image": "vllm/vllm-openai:v0.10.2"
    }
  ],
  "volume": [
    {
      "date": "2026-08-08",
      "hardware": "h200_sxm",
      "datapoints": 24
    }
  ]
}

滚动查看完整示例。

500

提交查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET稳定/api/v1/framework-releases读取最新框架版本

返回 vLLM 和 SGLang 最新的非草稿、非预发布 GitHub 版本标签。null 表示上游查询没有可用版本。

参数

无需参数。

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/framework-releases'

响应

FrameworkReleases
200

框架键映射到版本标签或 null。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "additionalProperties": {
    "type": [
      "string",
      "null"
    ]
  }
}

响应示例

代码
{
  "vllm": "v0.10.2",
  "sglang": "v0.4.10"
}
500

版本查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET稳定/api/v1/latest-images读取最新运行镜像

返回每个基准配置和序列最近观测到的容器镜像。

参数

无需参数。

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/latest-images'

响应

LatestImageRows
200

最新镜像行。

媒体类型: application/json

响应结构

代码
{
  "type": "array",
  "items": {
    "type": "object",
    "properties": {
      "model": {
        "type": "string"
      },
      "hardware": {
        "type": "string"
      },
      "framework": {
        "type": "string"
      },
      "precision": {
        "type": "string"
      },
      "spec_method": {
        "type": "string"
      },
      "disagg": {
        "type": "boolean"
      },
      "isl": {
        "type": [
          "number",
          "null"
        ]
      },
      "osl": {
        "type": [
          "number",
          "null"
        ]
      },
      "benchmark_type": {
        "type": "string"
      },
      "image": {
        "type": "string"
      },
      "date": {
        "type": "string",
        "format": "date"
      }
    },
    "required": [
      "model",
      "hardware",
      "framework",
      "precision",
      "spec_method",
      "disagg",
      "isl",
      "osl",
      "benchmark_type",
      "image",
      "date"
    ],
    "additionalProperties": false
  }
}

滚动查看完整示例。

响应示例

代码
[
  {
    "model": "dsr1",
    "hardware": "h200_sxm",
    "framework": "vllm",
    "precision": "fp8",
    "spec_method": "none",
    "disagg": false,
    "isl": 1024,
    "osl": 1024,
    "benchmark_type": "single_turn",
    "image": "vllm/vllm-openai:v0.10.2",
    "date": "2026-08-08"
  },
  {
    "model": "dsr1",
    "hardware": "h200_sxm",
    "framework": "vllm",
    "precision": "fp8",
    "spec_method": "none",
    "disagg": false,
    "isl": null,
    "osl": null,
    "benchmark_type": "agentic_traces",
    "image": "vllm/vllm-openai:v0.10.2",
    "date": "2026-08-08"
  }
]

滚动查看完整示例。

500

镜像查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}

数据集

数据集目录、元数据、会话索引与会话结构。

GET稳定/api/v1/datasets列出已导入的数据集

返回数据集目录卡片，不包含较大的 chart_data 字段。

参数

无需参数。

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/datasets'

响应

DatasetRecords
200

数据集目录记录。

媒体类型: application/json

响应结构

代码
{
  "type": "array",
  "items": {
    "type": "object",
    "properties": {
      "id": {
        "type": "string"
      },
      "slug": {
        "type": "string"
      },
      "label": {
        "type": "string"
      },
      "variant": {
        "type": "string"
      },
      "description": {
        "type": [
          "string",
          "null"
        ]
      },
      "hf_url": {
        "type": [
          "string",
          "null"
        ]
      },
      "license": {
        "type": [
          "string",
          "null"
        ]
      },
      "conversation_count": {
        "type": "integer"
      },
      "summary": {
        "type": "object",
        "additionalProperties": true
      },
      "ingested_at": {
        "type": "string",
        "format": "date-time"
      }
    },
    "required": [
      "id",
      "slug",
      "label",
      "variant",
      "description",
      "hf_url",
      "license",
      "conversation_count",
      "summary",
      "ingested_at"
    ],
    "additionalProperties": false
  }
}

滚动查看完整示例。

响应示例

代码
[
  {
    "id": "ds_01",
    "slug": "cc-traces-weka",
    "label": "CC Traces Weka",
    "variant": "default",
    "description": "Agentic coding traces",
    "hf_url": "https://huggingface.co/datasets/example/cc-traces-weka",
    "license": "Apache-2.0",
    "conversation_count": 1200,
    "summary": {
      "totalIn": 8200000,
      "totalOut": 1700000
    },
    "ingested_at": "2026-08-08T03:00:00Z"
  }
]

滚动查看完整示例。

500

数据集目录查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET稳定/api/v1/datasets/{slug}读取数据集详情

返回一条数据集目录记录及其预计算的 chart_data 分布。

参数

GET /api/v1/datasets/{slug}: 参数
名称位置类型要求说明示例
slugpathstring必填目录中的数据集 slug。cc-traces-weka

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/datasets/cc-traces-weka'

响应

DatasetDetail
200

包含 chart_data 的数据集元数据。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "slug": {
      "type": "string"
    },
    "label": {
      "type": "string"
    },
    "variant": {
      "type": "string"
    },
    "description": {
      "type": [
        "string",
        "null"
      ]
    },
    "hf_url": {
      "type": [
        "string",
        "null"
      ]
    },
    "license": {
      "type": [
        "string",
        "null"
      ]
    },
    "conversation_count": {
      "type": "integer"
    },
    "summary": {
      "type": "object",
      "additionalProperties": true
    },
    "ingested_at": {
      "type": "string",
      "format": "date-time"
    },
    "chart_data": {
      "type": "object",
      "additionalProperties": true
    }
  },
  "required": [
    "id",
    "slug",
    "label",
    "variant",
    "description",
    "hf_url",
    "license",
    "conversation_count",
    "summary",
    "ingested_at",
    "chart_data"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "id": "ds_01",
  "slug": "cc-traces-weka",
  "label": "CC Traces Weka",
  "variant": "default",
  "description": "Agentic coding traces",
  "hf_url": null,
  "license": "Apache-2.0",
  "conversation_count": 1200,
  "summary": {},
  "ingested_at": "2026-08-08T03:00:00Z",
  "chart_data": {
    "tokens": {
      "bins": [
        0,
        1000,
        2000
      ],
      "counts": [
        140,
        320
      ]
    }
  }
}

滚动查看完整示例。

404

没有使用此 slug 的数据集。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Not found"
}
500

数据集查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET稳定/api/v1/datasets/{slug}/conversations列出数据集会话

返回可搜索、排序和分页的会话索引。只包含计数，不包含完整会话结构。

参数

GET /api/v1/datasets/{slug}/conversations: 参数
名称位置类型要求说明示例
slugpathstring必填目录中的数据集 slug。cc-traces-weka
searchquerystring可选按会话 ID 搜索，会先去除首尾空格，最多 100 个字符。trace-018
limitqueryinteger可选每页数量；小于 1 时按 1 处理，大于 200 时按 200 处理。50
offsetqueryinteger可选从 0 开始的行偏移。负数会变为 0。0
sortqueryenum可选按 tokens、turns、subagents 或 id 排序。未知值回退到 tokens。tokens

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/datasets/cc-traces-weka/conversations?limit=50&offset=0&sort=tokens'

响应

ConversationList
200

总数和会话索引项。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "total": {
      "type": "integer"
    },
    "items": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "conv_id": {
            "type": "string"
          },
          "models": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "num_turns": {
            "type": "integer"
          },
          "num_subagent_groups": {
            "type": "integer"
          },
          "total_in": {
            "type": "integer"
          },
          "total_out": {
            "type": "integer"
          },
          "total_cached": {
            "type": "integer"
          }
        },
        "required": [
          "conv_id",
          "models",
          "num_turns",
          "num_subagent_groups",
          "total_in",
          "total_out",
          "total_cached"
        ],
        "additionalProperties": false
      }
    }
  },
  "required": [
    "total",
    "items"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "total": 1200,
  "items": [
    {
      "conv_id": "trace-018",
      "models": [
        "claude-sonnet-4"
      ],
      "num_turns": 42,
      "num_subagent_groups": 3,
      "total_in": 18200,
      "total_out": 4200,
      "total_cached": 9600
    }
  ]
}

滚动查看完整示例。

400

search 超过 100 个字符。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "search too long"
}
404

没有使用此 slug 的数据集。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Not found"
}
500

会话查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET稳定/api/v1/datasets/{slug}/conversations/{convId}读取会话结构

返回单个会话及可用于火焰图的嵌套结构。App Router 对每个路径值解码一次。

参数

GET /api/v1/datasets/{slug}/conversations/{convId}: 参数
名称位置类型要求说明示例
slugpathstring必填目录中的数据集 slug。cc-traces-weka
convIdpathstring必填会话 ID，必须与会话索引中列出的值完全一致。trace-018

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/datasets/cc-traces-weka/conversations/trace-018'

响应

ConversationDetail
200

会话计数和嵌套结构。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "conv_id": {
      "type": "string"
    },
    "models": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "num_turns": {
      "type": "integer"
    },
    "num_subagent_groups": {
      "type": "integer"
    },
    "total_in": {
      "type": "integer"
    },
    "total_out": {
      "type": "integer"
    },
    "total_cached": {
      "type": "integer"
    },
    "structure": {
      "type": "object",
      "additionalProperties": true
    }
  },
  "required": [
    "conv_id",
    "models",
    "num_turns",
    "num_subagent_groups",
    "total_in",
    "total_out",
    "total_cached",
    "structure"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "conv_id": "trace-018",
  "models": [
    "claude-sonnet-4"
  ],
  "num_turns": 42,
  "num_subagent_groups": 3,
  "total_in": 18200,
  "total_out": 4200,
  "total_cached": 9600,
  "structure": {
    "name": "trace-018",
    "children": []
  }
}

滚动查看完整示例。

404

数据集或会话不存在。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Not found"
}
500

会话查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}

CollectiveX

带版本的集合通信扫描结果与运行发现数据。

GET测试版/api/v1/collectivex/latest读取最新 CollectiveX 数据集

按需发现并导入最新扫描，然后返回带版本的中立数据集。若刷新失败，会返回已存储的运行。

参数

GET /api/v1/collectivex/latest: 参数
名称位置类型要求说明示例
versionqueryenum必填CollectiveX 契约版本。1

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/collectivex/latest?version=1'

响应

CollectiveXDataset
200

最新的 CollectiveX 运行记录、覆盖情况、序列，以及可能存在的 KV 测试用例。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "version": {
      "type": "integer"
    },
    "run": {
      "type": "object",
      "properties": {
        "run_id": {
          "type": "string"
        },
        "run_attempt": {
          "type": "integer"
        },
        "generated_at": {
          "type": "string",
          "format": "date-time"
        },
        "conclusion": {
          "type": [
            "string",
            "null"
          ]
        },
        "source_sha": {
          "type": "string"
        },
        "requested_cases": {
          "type": "integer"
        },
        "terminal_cases": {
          "type": "integer"
        },
        "measured_cases": {
          "type": "integer"
        },
        "unsupported_cases": {
          "type": "integer"
        },
        "failed_cases": {
          "type": "integer"
        },
        "requested_points": {
          "type": "integer"
        },
        "terminal_points": {
          "type": "integer"
        },
        "measured_points": {
          "type": "integer"
        },
        "covered_skus": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "kv_requested_cases": {
          "type": "integer"
        },
        "kv_measured_cases": {
          "type": "integer"
        }
      },
      "required": [
        "run_id",
        "run_attempt",
        "generated_at",
        "conclusion",
        "source_sha",
        "requested_cases",
        "terminal_cases",
        "measured_cases",
        "unsupported_cases",
        "failed_cases",
        "requested_points",
        "terminal_points",
        "measured_points",
        "covered_skus"
      ],
      "additionalProperties": false
    },
    "coverage": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "series": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "kv": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    }
  },
  "required": [
    "version",
    "run",
    "coverage",
    "series"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "version": 1,
  "run": {
    "run_id": "123456789",
    "run_attempt": 1,
    "generated_at": "2026-08-08T03:00:00Z",
    "conclusion": "success",
    "source_sha": "0123456789abcdef",
    "requested_cases": 12,
    "terminal_cases": 12,
    "measured_cases": 10,
    "unsupported_cases": 2,
    "failed_cases": 0,
    "requested_points": 48,
    "terminal_points": 48,
    "measured_points": 40,
    "covered_skus": [
      "h200_sxm"
    ],
    "kv_requested_cases": 4,
    "kv_measured_cases": 4
  },
  "coverage": [],
  "series": [],
  "kv": []
}

滚动查看完整示例。

400

version 缺失或不受支持。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Unknown version"
}
404

没有已存储或可发现的运行。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Not found"
}
502

上游扫描发现不可用，且没有已存储的回退数据。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Unavailable"
}
503

上游扫描处理暂时不可用。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Unavailable"
}
500

已存储运行查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/collectivex/runs列出 CollectiveX 运行

返回逐步发现的运行汇总。discovery_complete=false 表示仍在发现更早的运行，客户端可以轮询。

参数

GET /api/v1/collectivex/runs: 参数
名称位置类型要求说明示例
versionqueryenum必填CollectiveX 契约版本。1

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/collectivex/runs?version=1'

响应

CollectiveXRunList
200

版本、运行汇总和发现状态。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "version": {
      "type": "integer"
    },
    "runs": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "run_id": {
            "type": "string"
          },
          "run_attempt": {
            "type": "integer"
          },
          "generated_at": {
            "type": "string",
            "format": "date-time"
          },
          "conclusion": {
            "type": [
              "string",
              "null"
            ]
          },
          "covered_skus": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "requested_cases": {
            "type": "integer"
          },
          "measured_cases": {
            "type": "integer"
          },
          "requested_points": {
            "type": "integer"
          },
          "terminal_points": {
            "type": "integer"
          },
          "terminal_counts": {
            "type": "object",
            "properties": {
              "measured": {
                "type": "integer"
              },
              "unsupported": {
                "type": "integer"
              },
              "failed": {
                "type": "integer"
              }
            },
            "required": [
              "measured",
              "unsupported",
              "failed"
            ],
            "additionalProperties": false
          },
          "kv_cases": {
            "type": "object",
            "properties": {
              "requested": {
                "type": "integer"
              },
              "measured": {
                "type": "integer"
              }
            },
            "required": [
              "requested",
              "measured"
            ],
            "additionalProperties": false
          }
        },
        "required": [
          "run_id",
          "run_attempt",
          "generated_at",
          "conclusion",
          "covered_skus",
          "requested_cases",
          "measured_cases",
          "requested_points",
          "terminal_points",
          "terminal_counts"
        ],
        "additionalProperties": false
      }
    },
    "discovery_complete": {
      "type": "boolean"
    }
  },
  "required": [
    "version",
    "runs",
    "discovery_complete"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "version": 1,
  "runs": [
    {
      "run_id": "123456789",
      "run_attempt": 1,
      "generated_at": "2026-08-08T03:00:00Z",
      "conclusion": "success",
      "covered_skus": [
        "h200_sxm"
      ],
      "requested_cases": 12,
      "measured_cases": 10,
      "requested_points": 48,
      "terminal_points": 48,
      "terminal_counts": {
        "measured": 40,
        "unsupported": 8,
        "failed": 0
      },
      "kv_cases": {
        "requested": 4,
        "measured": 4
      }
    }
  ],
  "discovery_complete": true
}

滚动查看完整示例。

400

version 缺失或不受支持。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Unknown version"
}
502

发现失败，且没有已存储的运行列表。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Unavailable"
}
503

发现暂时不可用。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Unavailable"
}
500

已存储运行列表查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/collectivex/runs/{runId}读取 CollectiveX 运行

按正整数运行 ID 返回带版本的 CollectiveX 数据集，并在可能时按需发现和导入。

参数

GET /api/v1/collectivex/runs/{runId}: 参数
名称位置类型要求说明示例
runIdpathinteger必填GitHub Actions 正整数运行 ID。123456789
versionqueryenum必填CollectiveX 契约版本。1

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/collectivex/runs/123456789?version=1'

响应

CollectiveXDataset
200

请求的 CollectiveX 数据集。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "version": {
      "type": "integer"
    },
    "run": {
      "type": "object",
      "properties": {
        "run_id": {
          "type": "string"
        },
        "run_attempt": {
          "type": "integer"
        },
        "generated_at": {
          "type": "string",
          "format": "date-time"
        },
        "conclusion": {
          "type": [
            "string",
            "null"
          ]
        },
        "source_sha": {
          "type": "string"
        },
        "requested_cases": {
          "type": "integer"
        },
        "terminal_cases": {
          "type": "integer"
        },
        "measured_cases": {
          "type": "integer"
        },
        "unsupported_cases": {
          "type": "integer"
        },
        "failed_cases": {
          "type": "integer"
        },
        "requested_points": {
          "type": "integer"
        },
        "terminal_points": {
          "type": "integer"
        },
        "measured_points": {
          "type": "integer"
        },
        "covered_skus": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "kv_requested_cases": {
          "type": "integer"
        },
        "kv_measured_cases": {
          "type": "integer"
        }
      },
      "required": [
        "run_id",
        "run_attempt",
        "generated_at",
        "conclusion",
        "source_sha",
        "requested_cases",
        "terminal_cases",
        "measured_cases",
        "unsupported_cases",
        "failed_cases",
        "requested_points",
        "terminal_points",
        "measured_points",
        "covered_skus"
      ],
      "additionalProperties": false
    },
    "coverage": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "series": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "kv": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    }
  },
  "required": [
    "version",
    "run",
    "coverage",
    "series"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "version": 1,
  "run": {
    "run_id": "123456789",
    "run_attempt": 1,
    "generated_at": "2026-08-08T03:00:00Z",
    "conclusion": "success",
    "source_sha": "0123456789abcdef",
    "requested_cases": 12,
    "terminal_cases": 12,
    "measured_cases": 10,
    "unsupported_cases": 2,
    "failed_cases": 0,
    "requested_points": 48,
    "terminal_points": 48,
    "measured_points": 40,
    "covered_skus": [
      "h200_sxm"
    ],
    "kv_requested_cases": 4,
    "kv_measured_cases": 4
  },
  "coverage": [],
  "series": [],
  "kv": []
}

滚动查看完整示例。

400

version 或 runId 无效。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Unknown version or run id"
}
404

该运行不存在。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Not found"
}
502

无法从上游来源获取该运行。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Unavailable"
}
503

上游处理暂时不可用。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Unavailable"
}
500

运行查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}

诊断读取

按结果提供跟踪、缓存、请求、同组结果和服务器指标诊断。

GET测试版/api/v1/agentic-aggregates读取智能体汇总百分位

按基准结果 ID 返回 ISL、OSL、KV 缓存利用率和前缀缓存命中率百分位。ID 会去重，最多接受 200 个。

参数

GET /api/v1/agentic-aggregates: 参数
名称位置类型要求说明示例
idsquerycomma-separated integers必填1 到 200 个正整数基准结果 ID。421,422

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/agentic-aggregates?ids=421,422'

响应

AgenticAggregateMap
200

结果 ID 映射到汇总百分位或 null 指标组。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "additionalProperties": {
    "type": "object",
    "properties": {
      "id": {
        "type": "integer"
      },
      "isl": {
        "oneOf": [
          {
            "type": "object",
            "properties": {
              "mean": {
                "type": "number"
              },
              "p50": {
                "type": "number"
              },
              "p75": {
                "type": "number"
              },
              "p90": {
                "type": "number"
              },
              "p95": {
                "type": "number"
              },
              "p99": {
                "type": "number"
              },
              "n": {
                "type": "integer"
              }
            },
            "required": [
              "mean",
              "p50",
              "p75",
              "p90",
              "p95",
              "p99",
              "n"
            ],
            "additionalProperties": false
          },
          {
            "type": "null"
          }
        ]
      },
      "osl": {
        "oneOf": [
          {
            "type": "object",
            "properties": {
              "mean": {
                "type": "number"
              },
              "p50": {
                "type": "number"
              },
              "p75": {
                "type": "number"
              },
              "p90": {
                "type": "number"
              },
              "p95": {
                "type": "number"
              },
              "p99": {
                "type": "number"
              },
              "n": {
                "type": "integer"
              }
            },
            "required": [
              "mean",
              "p50",
              "p75",
              "p90",
              "p95",
              "p99",
              "n"
            ],
            "additionalProperties": false
          },
          {
            "type": "null"
          }
        ]
      },
      "kvCacheUtil": {
        "oneOf": [
          {
            "type": "object",
            "properties": {
              "mean": {
                "type": "number"
              },
              "p50": {
                "type": "number"
              },
              "p75": {
                "type": "number"
              },
              "p90": {
                "type": "number"
              },
              "p95": {
                "type": "number"
              },
              "p99": {
                "type": "number"
              },
              "n": {
                "type": "integer"
              }
            },
            "required": [
              "mean",
              "p50",
              "p75",
              "p90",
              "p95",
              "p99",
              "n"
            ],
            "additionalProperties": false
          },
          {
            "type": "null"
          }
        ]
      },
      "prefixCacheHitRate": {
        "oneOf": [
          {
            "type": "object",
            "properties": {
              "mean": {
                "type": "number"
              },
              "p50": {
                "type": "number"
              },
              "p75": {
                "type": "number"
              },
              "p90": {
                "type": "number"
              },
              "p95": {
                "type": "number"
              },
              "p99": {
                "type": "number"
              },
              "n": {
                "type": "integer"
              }
            },
            "required": [
              "mean",
              "p50",
              "p75",
              "p90",
              "p95",
              "p99",
              "n"
            ],
            "additionalProperties": false
          },
          {
            "type": "null"
          }
        ]
      }
    },
    "required": [
      "id",
      "isl",
      "osl",
      "kvCacheUtil",
      "prefixCacheHitRate"
    ],
    "additionalProperties": false
  }
}

滚动查看完整示例。

响应示例

代码
{
  "421": {
    "id": 421,
    "isl": {
      "mean": 18320,
      "p50": 16440,
      "p75": 20110,
      "p90": 24880,
      "p95": 27940,
      "p99": 31900,
      "n": 512
    },
    "osl": null,
    "kvCacheUtil": null,
    "prefixCacheHitRate": null
  }
}

滚动查看完整示例。

400

ids 缺失、格式错误或超过 200 个唯一 ID。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "ids query param is required"
}
500

汇总查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/benchmark-siblings读取同组基准点

返回基准 SKU，以及同一硬件、框架、模型、精度、方法、基准类型和工作流运行中的全部点。

参数

GET /api/v1/benchmark-siblings: 参数
名称位置类型要求说明示例
idqueryinteger必填正整数基准结果 ID。421

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/benchmark-siblings?id=421'

响应

BenchmarkSiblings
200

SKU 元数据和同组导航行。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "sku": {
      "type": "object",
      "additionalProperties": true
    },
    "siblings": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    }
  },
  "required": [
    "sku",
    "siblings"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "sku": {
    "hardware": "h200_sxm",
    "framework": "vllm",
    "model": "dsr1",
    "precision": "fp8",
    "spec_method": "none",
    "benchmark_type": "agentic_traces",
    "github_run_id": 123456789,
    "date": "2026-08-08",
    "dataset_slug": "cc-traces-weka"
  },
  "siblings": [
    {
      "id": 421,
      "conc": 32,
      "offload_mode": "off",
      "decode_tp": 8,
      "decode_ep": 1,
      "decode_pp": null,
      "decode_dcp_size": 8,
      "decode_pcp_size": 1,
      "decode_dp_attention": false,
      "decode_num_workers": 1,
      "prefill_tp": 8,
      "prefill_ep": 1,
      "prefill_pp": null,
      "prefill_dcp_size": 8,
      "prefill_pcp_size": 1,
      "prefill_dp_attention": false,
      "prefill_num_workers": 1,
      "num_prefill_gpu": 0,
      "num_decode_gpu": 8,
      "disagg": false,
      "is_multinode": false,
      "tput_per_gpu": 128.4,
      "total_requests": 320,
      "is_current": true,
      "has_trace": true
    }
  ]
}

滚动查看完整示例。

400

id 缺失或无效。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "id is required (benchmark_result_id)"
}
404

没有使用此 ID 的基准结果。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Not found"
}
500

同组查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/derived-agentic-metrics读取派生智能体指标

按基准结果 ID 返回归一化交互性百分位。ID 会去重，最多接受 200 个。

参数

GET /api/v1/derived-agentic-metrics: 参数
名称位置类型要求说明示例
idsquerycomma-separated integers必填1 到 200 个正整数基准结果 ID。421,422

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/derived-agentic-metrics?ids=421,422'

响应

DerivedAgenticMetricMap
200

结果 ID 映射到 p75 和 p90 归一化交互性。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "additionalProperties": {
    "type": "object",
    "properties": {
      "id": {
        "type": "integer"
      },
      "p75_e2e_norm_intvty": {
        "type": [
          "number",
          "null"
        ]
      },
      "p90_e2e_norm_intvty": {
        "type": [
          "number",
          "null"
        ]
      }
    },
    "required": [
      "id",
      "p75_e2e_norm_intvty",
      "p90_e2e_norm_intvty"
    ],
    "additionalProperties": false
  }
}

滚动查看完整示例。

响应示例

代码
{
  "421": {
    "id": 421,
    "p75_e2e_norm_intvty": 31.2,
    "p90_e2e_norm_intvty": 24.8
  }
}
400

ids 缺失、格式错误或超过 200 个唯一 ID。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "ids query param is required"
}
500

派生指标查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/request-timeline读取请求时间线

返回带版本号的基准测试时间窗口，以及每个请求的重放标识、来源追溯信息、调度/确认/完成/取消时间、token 指标、阶段和 worker 信息。

参数

GET /api/v1/request-timeline: 参数
名称位置类型要求说明示例
idqueryinteger必填正整数基准结果 ID。421

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/request-timeline?id=421'

响应

RequestTimeline
200

时间线元数据和请求记录。纳秒事件字段是相对 startNs 的偏移。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "version": {
      "type": "integer"
    },
    "startNs": {
      "type": "integer"
    },
    "endNs": {
      "type": "integer"
    },
    "durationS": {
      "type": "number"
    },
    "requests": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "cid": {
            "type": "string"
          },
          "ri": {
            "type": "integer"
          },
          "ti": {
            "type": "integer"
          },
          "srcTrace": {
            "type": "string"
          },
          "srcOuter": {
            "type": "integer"
          },
          "srcInner": {
            "type": "integer"
          },
          "srcKind": {
            "type": "string"
          },
          "wid": {
            "type": "string"
          },
          "ad": {
            "type": "integer"
          },
          "phase": {
            "type": "string"
          },
          "credit": {
            "type": "integer"
          },
          "start": {
            "type": "integer"
          },
          "ack": {
            "type": [
              "number",
              "null"
            ]
          },
          "end": {
            "type": "integer"
          },
          "ttftMs": {
            "type": [
              "number",
              "null"
            ]
          },
          "tpotMs": {
            "type": [
              "number",
              "null"
            ]
          },
          "isl": {
            "type": [
              "number",
              "null"
            ]
          },
          "osl": {
            "type": [
              "number",
              "null"
            ]
          },
          "cancelled": {
            "type": "boolean"
          }
        },
        "required": [
          "cid",
          "ti",
          "wid",
          "ad",
          "phase",
          "credit",
          "start",
          "ack",
          "end",
          "ttftMs",
          "tpotMs",
          "isl",
          "osl",
          "cancelled"
        ],
        "additionalProperties": false
      }
    }
  },
  "required": [
    "version",
    "startNs",
    "endNs",
    "durationS",
    "requests"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "version": 6,
  "startNs": 1000000000,
  "endNs": 2400000000,
  "durationS": 1.4,
  "requests": [
    {
      "cid": "trace-018",
      "ri": 0,
      "ti": 0,
      "wid": "7",
      "ad": 0,
      "phase": "profiling",
      "credit": 0,
      "start": 1200000,
      "ack": 1800000,
      "end": 420000000,
      "ttftMs": 42.3,
      "tpotMs": 18.1,
      "isl": 18320,
      "osl": 410,
      "cancelled": false
    }
  ]
}

滚动查看完整示例。

400

id 缺失或无效。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "id is required (benchmark_result_id)"
}
404

该结果没有时间线。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Not found"
}
500

时间线查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/server-log读取基准服务器日志

返回某个基准测试结果 ID 对应的一份已存储的 .log/.out 文件。file 应使用 server-log-files 返回的文件名。可添加 offset 或 limit，按指定范围分块读取；添加 download=1 可将完整的所选文件作为文本附件流式下载。

参数

GET /api/v1/server-log: 参数
名称位置类型要求说明示例
idqueryinteger必填正整数基准结果 ID。421
filequerystring可选产物内的相对文件名。省略时读取主文件或旧版日志文件。results/router.log
offsetqueryinteger可选从零开始的字符偏移量。提供 offset 或 limit 后启用分块模式。0
limitqueryinteger可选分块字符数，范围为 1 到 262144，默认值为 65536。65536
downloadqueryinteger可选设为 1 时，将完整的所选文件作为文本附件流式下载；不能与 offset 或 limit 同时使用。1

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/server-log?id=421&file=results%2Frouter.log&offset=0&limit=65536'

响应

ServerLog | ServerLogChunk | text/plain attachment
200

基准结果 ID 和服务器日志文本；分块模式还会返回范围元数据。

媒体类型: application/json

响应结构

代码
{
  "oneOf": [
    {
      "type": "object",
      "properties": {
        "id": {
          "type": "integer"
        },
        "serverLog": {
          "type": "string"
        }
      },
      "required": [
        "id",
        "serverLog"
      ],
      "additionalProperties": false
    },
    {
      "type": "object",
      "properties": {
        "id": {
          "type": "integer"
        },
        "fileName": {
          "type": "string"
        },
        "serverLog": {
          "type": "string"
        },
        "offset": {
          "type": "integer"
        },
        "nextOffset": {
          "type": [
            "number",
            "null"
          ]
        }
      },
      "required": [
        "id",
        "fileName",
        "serverLog",
        "offset",
        "nextOffset"
      ],
      "additionalProperties": false
    }
  ]
}

滚动查看完整示例。

响应示例

代码
{
  "id": 421,
  "fileName": "results/router.log",
  "serverLog": "INFO router initialized\n",
  "offset": 0,
  "nextOffset": 24
}
400

id 缺失或无效。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "id is required (benchmark_result_id)"
}
404

该结果没有服务器日志。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Not found"
}
500

服务器日志查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/server-log-search搜索完整基准测试日志

在某个基准测试结果对应的所有已存储 .log/.out 文件中，按字面值执行不区分大小写的搜索。响应仅返回数量受限的上下文片段，无需传输完整日志文件。

参数

GET /api/v1/server-log-search: 参数
名称位置类型要求说明示例
idqueryinteger必填正整数基准结果 ID。421
qquerystring必填按字面值匹配的搜索文本，长度为 1 到 256 个字符。router ready
limitqueryinteger可选最多返回的匹配数，范围为 1 到 100，默认值为 50。50

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/server-log-search?id=421&q=router%20ready&limit=50'

响应

ServerLogSearchResult
200

数量有上限的匹配结果，包含文件名、字符偏移量和上下文文本。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "id": {
      "type": "integer"
    },
    "query": {
      "type": "string"
    },
    "matches": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "fileName": {
            "type": "string"
          },
          "offset": {
            "type": "integer"
          },
          "before": {
            "type": "string"
          },
          "match": {
            "type": "string"
          },
          "after": {
            "type": "string"
          }
        },
        "required": [
          "fileName",
          "offset",
          "before",
          "match",
          "after"
        ],
        "additionalProperties": false
      }
    },
    "truncated": {
      "type": "boolean"
    }
  },
  "required": [
    "id",
    "query",
    "matches",
    "truncated"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "id": 421,
  "query": "router ready",
  "matches": [
    {
      "fileName": "results/router.log",
      "offset": 128,
      "before": "INFO ",
      "match": "router ready",
      "after": " on port 8000\n"
    }
  ],
  "truncated": false
}

滚动查看完整示例。

400

搜索参数无效。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Invalid query"
}
500

完整日志搜索失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/server-log-files列出已存储的基准测试日志文件

列出匹配服务器日志产物中保留的所有 .log 和 .out 文件名。路径相对于产物根目录返回，主文件排在首位。

参数

GET /api/v1/server-log-files: 参数
名称位置类型要求说明示例
idqueryinteger必填正整数基准结果 ID。421

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/server-log-files?id=421'

响应

ServerLogFileNames
200

相对于产物根目录的 .log/.out 文件名。

媒体类型: application/json

响应结构

代码
{
  "type": "array",
  "items": {
    "type": "string"
  }
}

响应示例

代码
[
  "results/server.log",
  "results/benchmark.log",
  "results/router.log"
]
400

id 缺失或无效。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "id is required (benchmark_result_id)"
}
404

该结果没有日志文件集合。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Not found"
}
500

日志文件名查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/log-availability检查服务器日志可用性

仅返回具有已存储服务器日志的基准结果 ID。ID 会去重，最多接受 500 个。

参数

GET /api/v1/log-availability: 参数
名称位置类型要求说明示例
idsquerycomma-separated integers必填1 到 500 个正整数基准结果 ID。421,422

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/log-availability?ids=421,422'

响应

LogAvailabilityMap
200

可用结果 ID 映射为 true。缺失的键表示没有服务器日志。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "additionalProperties": {
    "type": "boolean"
  }
}

响应示例

代码
{
  "421": true
}
400

ids 缺失、格式错误或超过 500 个唯一 ID。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Expected ids as comma-separated positive integers"
}
500

服务器日志可用性查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/trace-availability检查跟踪可用性

仅返回具有已存储跟踪的基准结果 ID。ID 会去重，最多接受 500 个。

参数

GET /api/v1/trace-availability: 参数
名称位置类型要求说明示例
idsquerycomma-separated integers必填1 到 500 个正整数基准结果 ID。421,422

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/trace-availability?ids=421,422'

响应

TraceAvailabilityMap
200

可用结果 ID 映射为 true。缺失的键表示没有跟踪。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "additionalProperties": {
    "type": "boolean"
  }
}

响应示例

代码
{
  "421": true
}
400

ids 缺失、格式错误或超过 500 个唯一 ID。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "ids query param is required"
}
500

跟踪可用性查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/trace-histograms读取跟踪直方图

按基准结果 ID 返回输入和输出 token 计数数组。ID 会去重，最多接受 200 个。

参数

GET /api/v1/trace-histograms: 参数
名称位置类型要求说明示例
idsquerycomma-separated integers必填1 到 200 个正整数基准结果 ID。421,422

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/trace-histograms?ids=421,422'

响应

TraceHistogramMap
200

结果 ID 映射到原始 ISL 和 OSL 样本。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "additionalProperties": {
    "type": "object",
    "properties": {
      "id": {
        "type": "integer"
      },
      "isl": {
        "type": "array",
        "items": {
          "type": "number"
        }
      },
      "osl": {
        "type": "array",
        "items": {
          "type": "number"
        }
      }
    },
    "required": [
      "id",
      "isl",
      "osl"
    ],
    "additionalProperties": false
  }
}

滚动查看完整示例。

响应示例

代码
{
  "421": {
    "id": 421,
    "isl": [
      18220,
      19340,
      15110
    ],
    "osl": [
      410,
      380,
      512
    ]
  }
}

滚动查看完整示例。

400

ids 缺失、格式错误或超过 200 个唯一 ID。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "ids query param is required"
}
500

直方图查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}
GET测试版/api/v1/trace-server-metrics读取跟踪服务器指标

返回数据点元数据，以及可直接用于图表的聚合时间序列，涵盖缓存使用率、队列深度、prefill/decode 吞吐量和 prompt token 来源。metricSources 包含各来源的描述信息；仅当用户在数据点详情界面选择某个来源时，才会加载该来源对应的数组。

参数

GET /api/v1/trace-server-metrics: 参数
名称位置类型要求说明示例
idqueryinteger必填正整数基准结果 ID。421

请求

代码
curl -sS 'https://inferencex.semianalysis.com/api/v1/trace-server-metrics?id=421'

响应

TraceServerMetrics
200

点元数据、窗口边界和服务器指标序列。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "meta": {
      "type": "object",
      "additionalProperties": true
    },
    "startNs": {
      "type": "integer"
    },
    "endNs": {
      "type": "integer"
    },
    "durationS": {
      "type": "number"
    },
    "timeslicesCount": {
      "type": "integer"
    },
    "kvCacheUsage": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "prefixCacheHitRate": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "queueDepth": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "promptTokensBySource": {
      "type": "object",
      "additionalProperties": {
        "type": "array",
        "items": {
          "type": "object",
          "additionalProperties": true
        }
      }
    },
    "prefillTps": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "decodeTps": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "prefixCacheHitsTps": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "hostKvCacheUsage": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "kvCacheUsageByEngine": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    },
    "kvCachePoolTokens": {
      "type": [
        "number",
        "null"
      ]
    },
    "metricSources": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      }
    }
  },
  "required": [
    "meta",
    "startNs",
    "endNs",
    "durationS",
    "timeslicesCount",
    "kvCacheUsage",
    "prefixCacheHitRate",
    "queueDepth",
    "promptTokensBySource",
    "prefillTps",
    "decodeTps",
    "prefixCacheHitsTps",
    "hostKvCacheUsage",
    "kvCacheUsageByEngine",
    "kvCachePoolTokens",
    "metricSources"
  ],
  "additionalProperties": false
}

滚动查看完整示例。

响应示例

代码
{
  "meta": {
    "id": 421,
    "hardware": "h200_sxm",
    "framework": "vllm",
    "model": "dsr1",
    "conc": 32,
    "date": "2026-08-08"
  },
  "startNs": 1000000000,
  "endNs": 2400000000,
  "durationS": 1.4,
  "timeslicesCount": 2,
  "kvCacheUsage": [
    {
      "t": 0,
      "v": 0.44
    }
  ],
  "prefixCacheHitRate": [],
  "queueDepth": [],
  "promptTokensBySource": {},
  "prefillTps": [],
  "decodeTps": [],
  "prefixCacheHitsTps": [],
  "hostKvCacheUsage": [],
  "kvCacheUsageByEngine": [],
  "kvCachePoolTokens": 983040,
  "metricSources": []
}

滚动查看完整示例。

400

id 缺失或无效。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "id is required (benchmark_result_id)"
}
404

该结果没有服务器指标。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Not found"
}
500

服务器指标查询失败。

媒体类型: application/json

响应结构

代码
{
  "type": "object",
  "properties": {
    "error": {
      "type": "string"
    }
  },
  "required": [
    "error"
  ],
  "additionalProperties": true
}

响应示例

代码
{
  "error": "Internal server error"
}