{"uid":"cap_jJHL14YUgAU0L_1j-QVy9","slug":"tenk-inference-chip-index-rank-inference-chips-dd568a5e","name":"TenK Inference Chip Index – Rank Inference Chips","description":"Rank verified MLPerf Inference v6.0 Closed-division accelerators for one exact slice. Never a universal fastest chip.","url":"https://inference-chip-index-rank.tenkchipindex.workers.dev/api/agent/entrypoints/rank-inference-chips/invoke","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"input":{"type":"object","required":["sliceId"],"properties":{"page":{"type":"integer","minimum":1},"sliceId":{"type":"string","description":"Exact comparison slice ID. Primary: v6.0|closed|llama3.1-8b|Offline|99|tokens_per_second"},"vendors":{"type":"array","items":{"type":"string"},"description":"Optional vendor filter, e.g. NVIDIA, Intel, AMD."},"grouping":{"enum":["all-systems","best-per-accelerator"],"type":"string"},"pageSize":{"type":"integer","maximum":50,"minimum":1},"metricView":{"enum":["official","derived"],"type":"string","description":"official = submitted-system result; derived = per-accelerator when count is known."}},"description":"Rank query. sliceId is required; other fields are optional filters."}}},"responseSchema":{"type":"json","example":{"output":{"page":1,"rows":[{"rank":2,"unit":"tok/s","source":{"url":"https://github.com/mlcommons/inference_results_v6.0/blob/4d3916ac9cf474b679cdfcf492d43a0559418ad1/closed/NVIDIA/results/B300-SXM-270GBx8_TRT/llama3.1-8b/Offline/performance/run_1/mlperf_log_summary.txt","path":"closed/NVIDIA/results/B300-SXM-270GBx8_TRT/llama3.1-8b/Offline/performance/run_1/mlperf_log_summary.txt","commit":"4d3916ac9cf474b679cdfcf492d43a0559418ad1","sha256":"95a6bd7cd7435f12f536bea03306ca0a36ff8a0262cc78c5fb150067ad636e33","repository":"https://github.com/mlcommons/inference_results_v6.0"},"position":2,"systemId":"B300-SXM-270GBx8_TRT","logicalId":"res:NVIDIA:B300-SXM-270GBx8_TRT:llama3.1-8b:Offline:99:tokens_per_second","submitter":"NVIDIA","systemName":"NVIDIA DGX B300 (8x B300-SXM-270GB, TensorRT)","officialValue":165432,"displayedLabel":"official submitted system","displayedValue":165432,"acceleratorSlug":"nvidia-b300-sxm-270gb","acceleratorCount":8,"acceleratorFamily":"B300","acceleratorVendor":"NVIDIA","derivedPerAccelerator":20679,"acceleratorDisplayName":"NVIDIA B300 SXM 270GB"}],"slice":{"unit":"tok/s","release":"v6.0","sliceId":"v6.0|closed|llama3.1-8b|Offline|99|tokens_per_second","division":"closed","scenario":"Offline","workload":"llama3.1-8b","metricKey":"tokens_per_second","acceptedCount":23,"comparability":"Comparable only for MLPerf Inference v6.0 Closed division, workload llama3.1-8b, scenario Offline, accuracy target 99%, metric Tokens per second (system) in tok/s.","accuracyTarget":"99","winningDirection":"higher"},"total":23,"grouping":"all-systems","pageSize":10,"metricView":"official","sourceLinks":["https://github.com/mlcommons/inference_results_v6.0/blob/4d3916ac9cf474b679cdfcf492d43a0559418ad1/closed/NVIDIA/results/B300-SXM-270GBx8_TRT/llama3.1-8b/Offline/performance/run_1/mlperf_log_summary.txt"],"comparability":"Comparable only for MLPerf Inference v6.0 Closed division, workload llama3.1-8b, scenario Offline, accuracy target 99%, metric Tokens per second (system) in tok/s.","datasetVersion":"chip-index-v6.0-full-source-3d26cfcc5423"}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_v8-M4pc0pz_GSTZp6-aRP","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Returns a ranked list of MLPerf Inference v6.0 Closed-division accelerators for a specific benchmark slice (e.g. Llama 3.1-8B Offline throughput).","exampleAgentPrompt":"Using the TenK Chip Index, rank all verified MLPerf Inference v6.0 closed-division accelerators for the Llama 3.1-8B Offline 99% accuracy slice (sliceId: v6.0|closed|llama3.1-8b|Offline|99|tokens_per_second), grouped by best-per-accelerator and show derived per-accelerator throughput.","exampleUseCases":[{"title":"Pick fastest LLM inference chip","prompt":"Which accelerator tops the MLPerf v6.0 closed-division leaderboard for Llama 3.1-8B offline inference in tokens per second? Show me the best-per-accelerator ranking using sliceId v6.0|closed|llama3.1-8b|Offline|99|tokens_per_second."},{"title":"Vendor comparison for hardware procurement","prompt":"I'm evaluating AI inference hardware — can you pull the MLPerf v6.0 closed-division rankings for Llama 3.1-8B Offline throughput and filter to only show NVIDIA and AMD systems so I can compare their official submitted scores?"},{"title":"Audit benchmark source provenance","prompt":"For the top-ranked systems in the MLPerf Inference v6.0 closed division Llama 3.1-8B Offline slice, can you fetch the rankings and include the source GitHub log URLs so I can verify the raw benchmark results myself?"}],"resultDescription":"A paginated JSON response containing: the slice metadata (workload, scenario, accuracy target, metric, comparability statement, winning direction), a ranked list of rows (each with rank, system name, submitter, accelerator vendor/family/display name, official submitted value, derived per-accelerator value, count, and a direct GitHub source log URL for audit), plus total count, grouping mode, and metric view used.","failureModes":["Invalid or unknown sliceId returns an error — only exact MLPerf v6.0 slice IDs are accepted","Vendor filter that matches no entries returns an empty rows array","pageSize exceeding 50 is rejected by schema validation","Network or worker timeout on the Cloudflare edge","Payment failure (x402 protocol) if USDC balance is insufficient or wallet is not configured"],"whenToPreferThis":"Choose this endpoint when you need authoritative, independently-verified MLPerf Inference v6.0 Closed-division benchmark rankings for a specific workload slice. It is the right choice when reproducibility and provenance matter — every result links back to the official MLCommons GitHub commit. Prefer it over vendor marketing sheets, third-party review sites, or general LLM knowledge when you need a structured, comparable, auditable leaderboard that an AI agent can programmatically consume and filter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:34:59.206Z","isFirstParty":false}