{"listing":{"listing_type":"product","name":"OneTriangle","slug":"onetriangle-api","tagline":"Inference engine that cuts LLM inference costs and latency by 20% using KV cache transfer between a small prefill model and a large decode model.","description":"OneTriangle runs prefill on a smaller model and decode on a larger one, transferring per-layer key/value tensors projected into the target model's attention space. This eliminates the cost of large-model prefill on long inputs, which typically dominates inference bills. The system gates each model pair on quality and latency thresholds and falls back to standard prefill when a pair does not meet them. It supports open-weight models including Llama, Qwen, Mistral, Gemma, and DeepSeek, with OneTriangle managing the GPU infrastructure.\n\nOneTriangle is a product of OneTriangle.","url":"https://onetriangle.ai/","is_stealth":false,"normalized_domain":"onetriangle.ai","normalized_url_key":"onetriangle.ai","parent_slug":"onetriangle","parent":{"slug":"onetriangle","name":"OneTriangle","listing_type":"company","profile_url":"/companies/onetriangle"},"type_data":{"product_kind":"api","platforms":["api"],"open_source":false,"use_cases":["reduce LLM inference costs","reduce inference latency","serve open-weight models","KV cache-optimized inference"],"integrations":["Llama","Qwen","Mistral","Gemma","DeepSeek"]},"logo":null,"links":[],"entry_points":[{"kind":"contact","url":"https://onetriangle.ai/","audience":"any","primary":false,"listed_by":"community","on_listing_domain":true}],"primary_entry_points":{"human":{"kind":"contact","url":"https://onetriangle.ai/","audience":"any","primary":false,"listed_by":"community","on_listing_domain":true},"agent":null},"founders":[],"media":null,"categories":["AI","Infrastructure","Developer Tools","B2B","Artificial Intelligence","Open Source"],"stage":null,"founded_year":null,"location":null,"pricing":null,"twitter":null,"github":null,"linkedin":null,"contact_email":null,"added_at":"2026-09-05T04:32:20.665Z","added_via":"web","geo":{"keywords":["OneTriangle","OneTriangle","AI","Infrastructure","Developer Tools","B2B","Artificial Intelligence","Open Source"],"canonical_facts":["Product of OneTriangle"]},"agents":null,"featured_until":null,"example":false,"ownership_status":"unclaimed","claimed_by_agent_id":null,"claimed_via_claim_id":null,"claimed_at":null,"updated_at":"2026-09-05T04:32:20.665Z","is_featured":false,"category_memberships":[{"kind":"product_category","slug":"ai","name":"AI","note":null,"profile_url":"/categories/ai"},{"kind":"product_category","slug":"artificial-intelligence","name":"Artificial Intelligence","note":null,"profile_url":"/categories/artificial-intelligence"},{"kind":"product_category","slug":"b2b","name":"B2B","note":null,"profile_url":"/categories/b2b"},{"kind":"product_category","slug":"developer-tools","name":"Developer Tools","note":null,"profile_url":"/categories/developer-tools"},{"kind":"product_category","slug":"infrastructure","name":"Infrastructure","note":null,"profile_url":"/categories/infrastructure"},{"kind":"product_category","slug":"open-source","name":"Open Source","note":null,"profile_url":"/categories/open-source"}]}}