{"eid":"ovh-2","name":"OVHcloud AI Endpoints","domain":"ovh.net","resolved_by":"domain","topics":["inference"],"n_records":1,"best_vorder":0,"review":null,"aliases":["OVHcloud AI Endpoints","OVHcloud AI Endpoints (anonymous tier)","ovh.net"],"records":[{"rid":"inference/ovh-ai-endpoints","card":{"rid":"inference/ovh-ai-endpoints","eid":"ovh-2","topic":"inference","slug":"ovh-ai-endpoints","provider":"OVHcloud AI Endpoints (anonymous tier)","url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","domain":"ovh.net","category":"inference endpoint, keyless","tier":null,"verdict":"qualifies","vorder":0,"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":"2026-10-22T03:16:16.000Z","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; 22 model ids on /v1/models, each carrying a pricing object in USD per token. Twelve of the 22 are chat models and two of those, Qwen3Guard-G...","duplicate_of":null,"n_unknown":10},"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 complete no-account stack; the two-a-minute ceiling is the scarce link, not the agent","limits":[{"kind":"request-rate","value":"x-ratelimit-limit-minute: 2, ratelimit-reset: 34 seconds","source":"response header from a live POST, 2026-10-22T03:17:26Z"}],"slug":"ovh-ai-endpoints","provider":"OVHcloud AI Endpoints (anonymous tier)","url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1","category":"inference endpoint, keyless","free_tier":{"stated":"no key required; 22 model ids on /v1/models, each carrying a pricing object in USD per token. Twelve of the 22 are chat models and two of those, Qwen3Guard-Gen-0.6B and Qwen3Guard-Gen-8B, price at exactly zero on prompt and completion. The other 10 ids are one image model, three embedding models, four TTS models and two ASR models","unit":"tokens","metered_on":"request-count","source_url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/models","read_on":"2026-10-22","notes":"the pricing object is published per model and is the machine form of 'free'. Qwen3Guard-Gen-0.6B and Qwen3Guard-Gen-8B are the only two chat models priced at exactly zero on both prompt and completion. No chat model is priced at 0.00000001 USD: that figure belongs to the two embedding models bge-m3 and bge-multilingual-gemma2"},"endpoint":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions","identity_cost":{"kind":"anonymous","detail":"no Authorization header is sent and none is required. The prober's per-endpoint track record reports 244 of 343 calls answered over 14 days from its own IP, 71 per cent, and 244 of the 267 calls OVH accepted for a model it serves, 91 per cent","country":null},"reliability_note":"the per-minute ceiling is 2, published in the response headers, so a burst is refused with 429 rather than throttled","confidence":"measured","confidence_note":"eight models were called twice. The header ceiling was read from a live response. What is not measured is whether the zero price survives signup.","probe":{"records":[{"probe_id":"ovh-qwen3guard","requested_model":"Qwen3Guard-Gen-0.6B","http_run1":200,"http_run2":200,"answered_run1":"yes","answered_run2":"yes","model_echoed":"Qwen3Guard-Gen-0.6B","echo_match":"yes","latency_ms_run1":4228,"latency_ms_run2":4020,"ttft_ms_run1":1411,"completion_tokens_run1":11,"tps_run1":"103.11","tps_run2":"91.75","tps_basis":null,"needle_echoed_run1":"no","body_bytes_run1":335,"body_sha256_16_run1":"00913865fb1fc4a9","reasoning_only":"no","error_run1":"","error_run2":""},{"probe_id":"ovh-gptoss20b","requested_model":"gpt-oss-20b","http_run1":200,"http_run2":200,"answered_run1":"yes","answered_run2":"yes","model_echoed":"gpt-oss-20b","echo_match":"yes","latency_ms_run1":1398,"latency_ms_run2":1241,"ttft_ms_run1":590,"completion_tokens_run1":51,"tps_run1":"12.02","tps_run2":"14.77","tps_basis":null,"needle_echoed_run1":"yes","body_bytes_run1":436,"body_sha256_16_run1":"4092e3cd74826e4e","reasoning_only":"no","error_run1":"","error_run2":""},{"probe_id":"ovh-qwen397b","requested_model":"Qwen3.5-397B-A17B","http_run1":200,"http_run2":200,"answered_run1":"no","answered_run2":"no","model_echoed":"Qwen3.5-397B-A17B","echo_match":"yes","latency_ms_run1":4164,"latency_ms_run2":2261,"ttft_ms_run1":"","completion_tokens_run1":256,"tps_run1":"","tps_run2":"","tps_basis":null,"needle_echoed_run1":"no","body_bytes_run1":1199,"body_sha256_16_run1":"b36f7a15edcc618a","reasoning_only":"yes","error_run1":"empty content; reasoning field populated (865 chars); finish_reason=length","error_run2":"empty content; reasoning field populated (995 chars); finish_reason=length"},{"probe_id":"ovh-llama70b","requested_model":"Meta-Llama-3_3-70B-Instruct","http_run1":200,"http_run2":200,"answered_run1":"yes","answered_run2":"yes","model_echoed":"Meta-Llama-3_3-70B-Instruct","echo_match":"yes","latency_ms_run1":1027,"latency_ms_run2":919,"ttft_ms_run1":639,"completion_tokens_run1":9,"tps_run1":"9.19","tps_run2":"8.98","tps_basis":null,"needle_echoed_run1":"yes","body_bytes_run1":307,"body_sha256_16_run1":"a76c1caf361d54a2","reasoning_only":"no","error_run1":"","error_run2":""},{"probe_id":"ovh-mistral-nemo","requested_model":"Mistral-Nemo-Instruct-2407","http_run1":200,"http_run2":200,"answered_run1":"yes","answered_run2":"yes","model_echoed":"Mistral-Nemo-Instruct-2407","echo_match":"yes","latency_ms_run1":1336,"latency_ms_run2":1250,"ttft_ms_run1":563,"completion_tokens_run1":9,"tps_run1":"3.67","tps_run2":"3.67","tps_basis":null,"needle_echoed_run1":"yes","body_bytes_run1":306,"body_sha256_16_run1":"bb415c52464d4e97","reasoning_only":"no","error_run1":"","error_run2":""},{"probe_id":"ovh-qwen38-27b","requested_model":"Qwen3.8-27B","http_run1":200,"http_run2":200,"answered_run1":"yes","answered_run2":"yes","model_echoed":"Qwen3.8-27B","echo_match":"yes","latency_ms_run1":2934,"latency_ms_run2":67293,"ttft_ms_run1":617,"completion_tokens_run1":57,"tps_run1":"27.64","tps_run2":"21.76","tps_basis":null,"needle_echoed_run1":"yes","body_bytes_run1":513,"body_sha256_16_run1":"2bf027e77c4d3a8e","reasoning_only":"no","error_run1":"","error_run2":""},{"probe_id":"ovh-qwen36-27b","requested_model":"Qwen3.6-27B","http_run1":200,"http_run2":200,"answered_run1":"yes","answered_run2":"no","model_echoed":"Qwen3.6-27B","echo_match":"yes","latency_ms_run1":3664,"latency_ms_run2":4311,"ttft_ms_run1":546,"completion_tokens_run1":211,"tps_run1":"","tps_run2":"","tps_basis":null,"needle_echoed_run1":"yes","body_bytes_run1":1070,"body_sha256_16_run1":"5a831ad2fb72237a","reasoning_only":"no","error_run1":"","error_run2":"empty content; reasoning field populated (930 chars); finish_reason=length"},{"probe_id":"ovh-gptoss120b","requested_model":"gpt-oss-120b","http_run1":200,"http_run2":200,"answered_run1":"yes","answered_run2":"yes","model_echoed":"gpt-oss-120b","echo_match":"yes","latency_ms_run1":7186,"latency_ms_run2":3701,"ttft_ms_run1":628,"completion_tokens_run1":124,"tps_run1":"22.67","tps_run2":"25.84","tps_basis":null,"needle_echoed_run1":"no","body_bytes_run1":819,"body_sha256_16_run1":"2d1306c00f54818d","reasoning_only":"no","error_run1":"","error_run2":""},{"probe_id":"ovh-qwen32b","requested_model":"Qwen3-32B","http_run1":404,"http_run2":404,"answered_run1":"no","answered_run2":"no","model_echoed":"","echo_match":"yes","latency_ms_run1":512,"latency_ms_run2":537,"ttft_ms_run1":"","completion_tokens_run1":0,"tps_run1":"","tps_run2":"","tps_basis":null,"needle_echoed_run1":"no","body_bytes_run1":130,"body_sha256_16_run1":"06d1e24ad072bd9c","reasoning_only":"no","error_run1":"{\"code\": \"model_not_found\", \"message\": \"The model `Qwen3-32B` does not exist.\", \"param\": null, \"type\": \"invalid_request_error\"}","error_run2":"{\"code\": \"model_not_found\", \"message\": \"The model `Qwen3-32B` does not exist.\", \"param\": null, \"type\": \"invalid_request_error\"}"}],"runs":["probes-w.json","probes-w-run2.json"],"conditions":"one machine, one IP, one country, 2026-10-22T03:02Z and 03:10Z"},"evidence":[{"url":"probe:https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions","date":"2026-10-22","proved":"gpt-oss-20b answered 200 with the requested model echoed and the needle present, 51 completion tokens, 1305 ms (run 1) and 1241 ms (run 2)"},{"url":"https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/models","date":"2026-10-22","proved":"22 model ids with context_length and a per-token pricing object, 12 of them chat models; Qwen3Guard-Gen-0.6B and -8B carry prompt 0 and completion 0; bge-m3 and bge-multilingual-gemma2 carry prompt 0.00000001 and are embeddings; the largest chat model, Qwen3.5-397B-A17B, carries prompt 0.00000071 and completion 0.00000425 USD per token at 262144 context"}],"verdict":"qualifies","verified_at":"2026-10-22T03:16:16.000Z","notes":"The endpoint answers without a key but publishes a price per token, so 'keyless' describes the authentication requirement and not the cost. The two guard models are genuinely zero. Qwen3.5-397B-A17B and Qwen3.6-27B return empty content at max_tokens 256 with the reasoning field populated and finish_reason length, which is budget exhaustion and not a failure.","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"],["$.probe.records[4].tps_basis","process"],["$.probe.records[5].tps_basis","process"],["$.probe.records[6].tps_basis","process"],["$.probe.records[7].tps_basis","process"],["$.probe.records[8].tps_basis","process"],["$.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":[]}]}