{"rid":"inference/llm7","card":{"rid":"inference/llm7","eid":"llm7","topic":"inference","slug":"llm7","provider":"LLM7","url":"https://api.llm7.io/v1","domain":"llm7.io","category":"inference endpoint, keyless","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":"2026-10-22T03:16:05.000Z","verified_basis":"live","checked_on":"2026-10-23","stale_on":"2026-11-22","n_evidence":2,"usd_month":null,"usd_per_tb_month":null,"summary":"no key required for the ids probed; /v1/models lists 68 ids, none with a zero price","duplicate_of":null,"n_unknown":6},"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; the undocumented rate ceiling is the scarce link, because a retry loop is needed and the ceiling it loops against is not published","limits":[{"kind":"request-rate","value":"unpublished. One 429 with retry_after 1 was observed on codestral-latest on 2026-10-22 after the same call answered; no rate-limit header is returned","source":"probe:https://api.llm7.io/v1/chat/completions, 2026-10-22"}],"slug":"llm7","provider":"LLM7","url":"https://api.llm7.io/v1","category":"inference endpoint, keyless","free_tier":{"stated":"no key required for the ids probed; /v1/models lists 68 ids, none with a zero price","unit":"tokens","metered_on":"request-count","source_url":"https://api.llm7.io/v1/models","read_on":"2026-10-22","notes":"the catalogue carries a per-model pricing object in USD per 1M tokens and every one is above zero, which makes the free access a quota rather than a price"},"endpoint":"https://api.llm7.io/v1/chat/completions","limits_note":"no rate-limit header was returned on a live call, and the ceiling was not probed by provoking 429s, which would spend an allowance belonging to someone else's service.","identity_cost":{"kind":"anonymous","detail":"no Authorization header sent and none required for the calls that answered. The prober's per-endpoint track record reports 380 of 1,029 calls answered over 14 days, 37 per cent, and 380 of the 556 calls LLM7 accepted for a model it offers, 68 per cent","country":null},"reliability_note":"one id was refused with 429 'Rate limit exceeded. Retry after 1 seconds' in the second run after answering in the first, eight minutes apart","confidence":"measured","confidence_note":"four ids were called twice. The answer rate is third-party; the 68 per cent figure is the prober's own accepted-only correction and both numbers are quoted because the headline one understates the endpoint. No quota is published, so the ceiling is measured only as 'it answered now'.","probe":{"records":[{"probe_id":"llm7-nemotron-nano","requested_model":"nemotron-3-nano:30b","http_run1":200,"http_run2":200,"answered_run1":"yes","answered_run2":"yes","model_echoed":"nemotron-3-nano:30b","echo_match":"yes","latency_ms_run1":817,"latency_ms_run2":631,"ttft_ms_run1":596,"completion_tokens_run1":100,"tps_run1":"53.12","tps_run2":"86.43","tps_basis":null,"needle_echoed_run1":"yes","body_bytes_run1":687,"body_sha256_16_run1":"95f1fdbbb16a9651","reasoning_only":"no","error_run1":"","error_run2":""},{"probe_id":"llm7-minimax-m27","requested_model":"minimax-m2.7","http_run1":200,"http_run2":200,"answered_run1":"yes","answered_run2":"yes","model_echoed":"minimax-m2.7","echo_match":"yes","latency_ms_run1":806,"latency_ms_run2":875,"ttft_ms_run1":648,"completion_tokens_run1":130,"tps_run1":"","tps_run2":"","tps_basis":null,"needle_echoed_run1":"yes","body_bytes_run1":845,"body_sha256_16_run1":"49ae7d6baf65bb5e","reasoning_only":"no","error_run1":"","error_run2":""},{"probe_id":"llm7-glm53-flash","requested_model":"GLM-5.3-Flash","http_run1":400,"http_run2":400,"answered_run1":"no","answered_run2":"no","model_echoed":"","echo_match":"yes","latency_ms_run1":339,"latency_ms_run2":339,"ttft_ms_run1":"","completion_tokens_run1":0,"tps_run1":"","tps_run2":"","tps_basis":null,"needle_echoed_run1":"no","body_bytes_run1":142,"body_sha256_16_run1":"d4857eb8fd0fa135","reasoning_only":"no","error_run1":"{\"message\": \"Model 'GLM-5.3-Flash' is currently unavailable.\", \"type\": \"invalid_request_error\", \"param\": null, \"code\": \"model_unavailable\"}","error_run2":"{\"message\": \"Model 'GLM-5.3-Flash' is currently unavailable.\", \"type\": \"invalid_request_error\", \"param\": null, \"code\": \"model_unavailable\"}"},{"probe_id":"llm7-codestral","requested_model":"codestral-latest","http_run1":200,"http_run2":429,"answered_run1":"yes","answered_run2":"no","model_echoed":"codestral-latest","echo_match":"yes","latency_ms_run1":775,"latency_ms_run2":349,"ttft_ms_run1":537,"completion_tokens_run1":9,"tps_run1":"","tps_run2":"","tps_basis":null,"needle_echoed_run1":"yes","body_bytes_run1":435,"body_sha256_16_run1":"e7633aa478740074","reasoning_only":"no","error_run1":"","error_run2":"{\"message\": \"Rate limit exceeded. Retry after 1 seconds.\", \"type\": \"rate_limit_error\", \"param\": null, \"code\": \"rate_limit_exceeded\", \"retry_after\": 1}"},{"probe_id":"llm7-deepseek-v4-flash","requested_model":"DeepSeek-V4-Flash-0731","http_run1":400,"http_run2":400,"answered_run1":"no","answered_run2":"no","model_echoed":"","echo_match":"yes","latency_ms_run1":437,"latency_ms_run2":319,"ttft_ms_run1":"","completion_tokens_run1":0,"tps_run1":"","tps_run2":"","tps_basis":null,"needle_echoed_run1":"no","body_bytes_run1":151,"body_sha256_16_run1":"bbe8badf4f6bc8aa","reasoning_only":"no","error_run1":"{\"message\": \"Model 'DeepSeek-V4-Flash-0731' is currently unavailable.\", \"type\": \"invalid_request_error\", \"param\": null, \"code\": \"model_unavailable\"}","error_run2":"{\"message\": \"Model 'DeepSeek-V4-Flash-0731' is currently unavailable.\", \"type\": \"invalid_request_error\", \"param\": null, \"code\": \"model_unavailable\"}"}],"runs":["probes-w.json","probes-w-run2.json"],"timing_note":"latency_ms and ttft_ms were taken from two different requests by the original instrument, so this record carried a row where ttft_ms exceeded latency_ms, which cannot happen on one call. The row is corrected from a re-probe on 2026-10-22T04:38:22Z with probe3.py, which derives both fields from one streaming request. The tps figures were always computed inside a single call and are unchanged."},"evidence":[{"url":"probe:https://api.llm7.io/v1/chat/completions","date":"2026-10-22","proved":"nemotron-3-nano:30b answered 200 with the model echoed and the needle present, 67 completion tokens, 672 ms in run 1 and 631 ms in run 2; codestral-latest answered in run 1 and returned 429 rate_limit_exceeded in run 2"},{"url":"https://api.llm7.io/v1/models","date":"2026-10-22","proved":"68 model ids each carrying a pricing object with input, output and cached_input in USD per 1M tokens; no id is priced at zero; glm-5.3 and deepseek-v4-flash:0731 are listed, while the two slugs the sweep sent, GLM-5.3-Flash and DeepSeek-V4-Flash-0731, are absent"}],"verdict":"qualifies-with-caveat","verified_at":"2026-10-22T03:16:05.000Z","notes":"The cleanest available ordering in the sweep: nemotron-3-nano:30b measured 53.12 and 86.43 tok/s and codestral-latest 127.60 and a 429. The two ids recorded as listed-but-refusing, GLM-5.3-Flash and DeepSeek-V4-Flash-0731, do not appear in /v1/models at all; the catalogue carries glm-5.3 and deepseek-v4-flash:0731, so a 400 on the unpublished slug proves nothing about the catalogue's honesty.","binding":"request-rate"},"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":[["$.probe.records[0].tps_basis","process"],["$.probe.records[1].tps_basis","process"],["$.probe.records[2].tps_basis","process"],["$.probe.records[3].tps_basis","process"],["$.probe.records[4].tps_basis","process"],["$.retention.stated","not-applicable"]],"history":[{"hid":"history/2026-10-22T044300Z/prober-answer-rate-denominator.md","when":"2026-10-22T04:43:00Z","status":"corrected","title":"The prober's answer rates were right and the reading of them was wrong"}],"drift":[]}