{"listing":{"listing_type":"product","name":"RunInfra","slug":"runinfra","tagline":"Optimize any Hugging Face model for production by benchmarking serving options and generating a deployable stack you own.","description":"RunInfra reads any Hugging Face model repo, benchmarks compatible serving engines (vLLM, SGLang, TensorRT-LLM), GPU targets, quantization, and KV cache configurations, and produces a deploy-ready stack with a benchmark receipt. Models can be run as REST endpoints on RunInfra-managed cloud or exported as a deployment kit for the customer's own hardware. The platform supports LLM, speech, embedding, vision, and image generation models across GPUs from L4 to H200 and B200. RunInfra is SOC 2 Type II attested.\n\nRunInfra is a product of RightNow.","url":"https://runinfra.ai/","is_stealth":false,"normalized_domain":"runinfra.ai","normalized_url_key":"runinfra.ai","parent_slug":"rightnow","parent":{"slug":"rightnow","name":"RightNow","listing_type":"company","profile_url":"/companies/rightnow"},"type_data":{"product_kind":"developer_tool","pricing_model":"usage_based","platforms":["web","api"],"open_source":false,"use_cases":["model optimization","GPU benchmarking","LLM deployment","open model serving","inference cost reduction"],"integrations":["Hugging Face","vLLM","SGLang","TensorRT-LLM"]},"logo":null,"links":[],"entry_points":[{"kind":"api","url":"https://runinfra.ai/","audience":"agent","primary":false,"listed_by":"community","on_listing_domain":true}],"primary_entry_points":{"human":null,"agent":{"kind":"api","url":"https://runinfra.ai/","audience":"agent","primary":false,"listed_by":"community","on_listing_domain":true}},"founders":[],"media":null,"categories":["AI","Infrastructure","Developer Tools","B2B"],"stage":null,"founded_year":null,"location":null,"pricing":"Pay per token for published Model API endpoints; usage-based for managed cloud","twitter":null,"github":null,"linkedin":null,"contact_email":null,"added_at":"2026-09-05T04:39:52.249Z","added_via":"web","geo":{"keywords":["RunInfra","RightNow","AI","Infrastructure","Developer Tools","B2B"],"canonical_facts":["Product of RightNow","Pricing (per product site): Pay per token for published Model API endpoints; usage-based for managed cloud"]},"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":"2026-09-05T04:39:52.249Z","is_featured":false,"category_memberships":[{"kind":"product_category","slug":"ai","name":"AI","note":null,"profile_url":"/categories/ai"},{"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"}]}}