{"rid":"inference/blockrun","card":{"rid":"inference/blockrun","eid":"blockrun","topic":"inference","slug":"blockrun","provider":"BlockRun","url":"https://blockrun.ai/api/v1","domain":"blockrun.ai","category":"inference relay","tier":null,"verdict":"qualifies-with-caveat","vorder":1,"grp":"usable","confidence":"measured","binding":"request-rate","identity_kind":"anonymous","identity_basis":"stated","needs_card":0,"needs_phone":0,"needs_id":0,"needs_institution":0,"country":null,"crypto":null,"interfaces":"rest","egress_metered":0,"per_object_bytes":null,"retention_days":null,"verified_at":"2026-10-22T03:15:25.000Z","verified_basis":"live","checked_on":"2026-10-23","stale_on":"2026-11-22","n_evidence":3,"usd_month":null,"usd_per_tb_month":null,"summary":"7 of 117 model ids on /v1/models carry an input price of 0; the rest carry list prices spanning openai, google, anthropic, xai, zai, bytedance, deepseek, qwe...","duplicate_of":null,"n_unknown":2},"record":{"topic":"inference","per_object_cap":{"stated":"not applicable: an inference endpoint stores nothing for the caller"},"retention":{"stated":"not applicable"},"egress":{"terms":"the response is the payload; no separate egress term is published","metered":false},"interface":["rest"],"tooling":"any OpenAI-compatible client; curl against POST {base}/chat/completions","chaining":"pairs with a free-standing agent as a relay of last resort; the scarce link is BlockRun's own upstream key, because its 429 arrives as FREE_MODEL_FAILED inside a 200","limits":[{"kind":"request-rate","value":"unpublished at BlockRun. The free route fails with FREE_MODEL_FAILED carrying debug 'NVIDIA API error: 429 Too Many Requests', so the observed ceiling belongs to BlockRun's own upstream key","source":"probe:https://blockrun.ai/api/v1/chat/completions, 2026-10-22"}],"slug":"blockrun","provider":"BlockRun","url":"https://blockrun.ai/api/v1","category":"inference relay","free_tier":{"stated":"7 of 117 model ids on /v1/models carry an input price of 0; the rest carry list prices spanning openai, google, anthropic, xai, zai, bytedance, deepseek, qwen, nvidia and eleven other families","unit":"tokens","metered_on":"request-count","source_url":"https://blockrun.ai/api/v1/models","read_on":"2026-10-22","notes":"the seven zero-priced ids are nvidia/nemotron-3-nano-omni-30b-a3b-reasoning, nvidia/nemotron-3.5-lightning, nvidia/llama-3.2-11b-vision, nvidia/nemotron-3-ultra-550b, cohere/north-mini-code, poolside/laguna-xs-2.1 and nvidia/muse-glimmer-30b"},"endpoint":"https://blockrun.ai/api/v1/chat/completions","identity_cost":{"kind":"anonymous","detail":"no Authorization header sent and none required for the free route","country":null},"reliability_note":"5 sequential identical calls answered 2 and refused 3 with FREE_MODEL_FAILED and a debug field naming 'NVIDIA API error: 429 Too Many Requests'","confidence":"measured","confidence_note":"the relay is proved by its own error body naming NVIDIA, and the substitution by the echoed model string. Both are measured; the upstream arrangement is inferred from them.","probe":{"records":[{"probe_id":"blockrun-gptoss20b","requested_model":"nvidia/gpt-oss-20b","http_run1":200,"http_run2":200,"answered_run1":"yes","answered_run2":"yes","model_echoed":"nvidia/gpt-oss-20b","echo_match":"yes","latency_ms_run1":2091,"latency_ms_run2":2543,"ttft_ms_run1":822,"completion_tokens_run1":51,"tps_run1":"12.92","tps_run2":"13.23","tps_basis":null,"needle_echoed_run1":"yes","body_bytes_run1":451,"body_sha256_16_run1":"056f8f161ffbc029","reasoning_only":"no","error_run1":"","error_run2":""}],"runs":["probes-w.json","probes-w-run2.json"]},"evidence":[{"url":"probe:https://blockrun.ai/api/v1/chat/completions","date":"2026-10-22","proved":"nvidia/gpt-oss-20b answered 200 and echoed nvidia/gpt-oss-20b's two runs, 2091 ms and 2543 ms, 51 completion tokens each"},{"url":"probe:https://blockrun.ai/api/v1/chat/completions","date":"2026-10-22","proved":"in the recon sweep eight minutes earlier, one of five sequential calls echoed nvidia/nemotron-3-super-120b for a nvidia/gpt-oss-20b request, and three returned FREE_MODEL_FAILED with debug 'NVIDIA API error: 429 Too Many Requests'"},{"url":"https://blockrun.ai/api/v1/models","date":"2026-10-22","proved":"117 model ids across 13 or more vendor families including openai, anthropic, google, xai and elevenlabs, with per-model long_context price tiers"}],"verdict":"qualifies-with-caveat","verified_at":"2026-10-22T03:15:25.000Z","notes":"The relay category's clearest instance. An error body that names a different vendor's API is the cheapest available tell, and the echoed model string is the second. A caller that does not compare the echoed model receives a plausible answer from a model it did not choose.","binding":"request-rate","binding_note":"the upstream NVIDIA 429 binds, and it arrives inside a 200-style error body rather than as a 429 status, so a client cannot see it by status code"},"claims":[{"path":"$.free_tier.stated","kind":"free-quota","num":null,"unit":null,"per":null,"currency":null,"usd":null,"fx_date":null,"parse":"unparsed"},{"path":"$.limits[0].value","kind":"limit:request-rate","num":null,"unit":null,"per":null,"currency":null,"usd":null,"fx_date":null,"parse":"unparsed"}],"unknown":[["$.probe.records[0].tps_basis","process"],["$.retention.stated","not-applicable"]],"history":[],"drift":[]}