{"schema_version":"1.1","active_field":{"id":"otb-20261110T173446Z","engine_commit":"d240badd966933fa19eec0606b2d1f3945f18ad2","started_at":"2026-11-10T17:34:46Z","gateways":["agentgateway","aisix","apisix","bifrost","busbar","gomodel","helicone","higress","kong","litellm-python","litellm-rust","one-api","plano","portkey","tensorzero"]},"definitions":{"definition-1":"WHAT THE GATEWAY ADDS, at concurrency 1. The gateway leg's percentile minus the same request taken straight to the mock, one at a time, both legs in the same window. No search and no threshold: there is nothing to stop early and nothing to decide. A difference at or below what the rig can resolve publishes `below_resolution` - the best result the comparison can express - and every surface renders that apart from a never-measured hole.","definition-2":"WHAT THE GATEWAY ADDS TO A STREAM, at concurrency 1: time to the first event, and the gaps between frames inside one stream, each as the gateway leg minus the same stream taken straight to the mock. Time-to-first-EVENT rather than first token, deliberately and by the same definition on both legs: a frame budget of one is satisfied by a dialect's opening scaffolding (openai sends a role delta, anthropic a `message_start`), so the quantity is the same on both sides and the difference still isolates what the gateway added."},"dataset_id":"dataset-c7c493902ee4473d65d1886e06f885af4adac2f4f5a4ea5fc70f2efa5f230c2f","generated_at":"2026-11-14T11:09:24.858Z","published_at":"2026-11-14T11:09:23.855Z","license":"https://creativecommons.org/licenses/by/4.0/","selected_protocol_pair":{"ingress_protocol":"openai","upstream_protocol":"openai"},"results":[{"gateway_id":"one-api","name":"One-API","gateway_build":"justsong/one-api:v0.6.10@sha256:af6b361630bdf408b86fce7aa8fc131b37ea5177ae866d121ba7c002e773e477","measured_at":"2026-11-10T17:39:58Z","published_at":"2026-11-14T11:09:23.855Z","generated_at":"2026-11-14T11:09:24.858Z","age_days":3,"age_as_of":"2026-11-14T11:09:24.858Z","age":"3 days old at collection generation","current_metadata":{"stars":37431,"stars_as_of":"2026-11-14","first_commit":"2023-04-22"},"status":{"state":"served","raw_state":true,"reason":null,"detail":null,"evidence_scope":"Recorded run evidence","probe_http_status":null,"response_excerpt":null},"metrics":{"added_latency_p50_us":{"value":34017,"certified":true,"suppressed":false,"state":"valid","reason":null,"section":"perf","definition_id":"definition-1"},"added_latency_p99_us":{"value":589609,"certified":true,"suppressed":false,"state":"valid","reason":null,"section":"perf","definition_id":"definition-1"},"added_ttft_p99_us":{"value":770,"certified":true,"suppressed":false,"state":"valid","reason":null,"section":"stream","definition_id":"definition-2"}},"provenance":{"source_url":"https://onthebench.ai/gateways/one-api","raw_result_url":"https://onthebench.ai/api/v1/runs/run-one-api-c9427cc70e392f48beb8e68d908f8924a7330748ac291dab1cd902b3f14c542f/raw.json","run_url":"https://onthebench.ai/gateways/runs/run-one-api-c9427cc70e392f48beb8e68d908f8924a7330748ac291dab1cd902b3f14c542f","methodology_url":"https://onthebench.ai/gateways/method","raw_sha256":"c9427cc70e392f48beb8e68d908f8924a7330748ac291dab1cd902b3f14c542f"},"evidence_url":"https://onthebench.ai/api/v1/measurements?gateway=one-api&ingress=openai&egress=openai"}],"comparison_policy":{"id":"matched-cell-v1","description":"Ratios require an identical protocol pair, hardware, architecture, metric definition, clean harness commit, recorded mock digest, and metric-specific workload. Missing evidence never matches missing evidence. These are observed gateway measurements against a local mock, not a claim about model latency or statistical significance."},"disclosure":{"operator":"Busbar team","operator_is_entrant":true},"interpretation":"Selected protocol cells, not a ranking. Check /api/v1/compare before calculating ratios. Null and below-resolution values are not zero. Repository statistics are dated metadata, not measurements. published_at is the recorded release timestamp, not the first publication of historical runs; null means unrecorded. generated_at is collection build time. Resolve metric definition_id through definitions."}
