{"id":"nr-who-serves-an-open-model-now-matters-as-much-as-which-model-you-pick-4a5cc7","slug":"who-serves-an-open-model-now-matters-as-much-as-which-model-you-pick-4a5cc7","type":"raw_signal","title":"Who serves an open model now matters as much as which model you pick","description":"Vals AI found cost differences of up to 2.3× between providers serving the same open-weight model on agent tasks, and the model makers' own APIs were neither the cheapest nor the fastest.","observed_at":"2026-10-25","record_date":"2026-10-25","date_kind":"observed_at","novelty":"notable","source_platform":"newruntime.com","topics":["google"],"entities":["Vals AI","Inference Provider Index","DeepSeek V4.1 Flash","Kimi K3","MiniMax M3","Together AI","Fireworks","Baseten","Google Cloud","Reflection"],"related_patterns":["agent-economics-moves-to-completed-work","harness-architecture-outlives-model-choice","verification-bandwidth-is-the-scarce-resource"],"source_url":"https://www.vals.ai/benchmarks/inference_provider","source_urls":["https://www.vals.ai/benchmarks/inference_provider","https://cloud.google.com/blog/topics/ai-infrastructure/day-0-support-with-5x-perf-for-reflection-beam-on-google-cloud","https://vllm.ai/blog/2026-10-23-deepseek-v41-flash-pd-wide-ep","https://github.com/vllm-project/vllm/pull/62009","https://www.bridgebench.ai/blog/the-methodology-of-nerfbench"],"why_it_matters":"Vals AI found cost differences of up to 2.3× between providers serving the same open-weight model on agent tasks, and the model makers' own APIs were neither the cheapest nor the fastest. Google Cloud reports up to 5x higher performance for Beam depending on the serving stack, and vLLM shows rack-scale tuning for DeepSeek. NerfBench now tracks whether a served model keeps performing as it did. That makes the endpoint something to benchmark and keep checking.","verification_level":"source-linked","signal_type":"synthesis","synthesis_of":[{"slug":"vals-ai-launched-the-inference-provider-index-comparing-60fbd1","title":"Vals AI launched the Inference Provider Index comparing open-weight model endpoints on agentic tasks.","url":"https://newruntime.com/posts/vals-ai-launched-the-inference-provider-index-comparing-60fbd1/"},{"slug":"google-cloud-offers-day-0-support-for-reflection-82afff","title":"Google Cloud offers day-0 support for Reflection's Beam open-weight model","url":"https://newruntime.com/posts/google-cloud-offers-day-0-support-for-reflection-82afff/"},{"slug":"full-engineering-writeup-covers-dep2-prefill-wide-ep-b2079d","title":"Full engineering writeup covers DEP2 prefill, Wide-EP decode, and CPU overhead fixes.","url":"https://newruntime.com/posts/full-engineering-writeup-covers-dep2-prefill-wide-ep-b2079d/"},{"slug":"speculative-decoding-uses-the-smaller-draft-model-to-48c074","title":"Speculative decoding uses the smaller draft model to propose tokens and the target model to verify them.","url":"https://newruntime.com/posts/speculative-decoding-uses-the-smaller-draft-model-to-48c074/"},{"slug":"the-methodology-of-nerfbench-7d0aa8","title":"The Methodology of NerfBench","url":"https://newruntime.com/posts/the-methodology-of-nerfbench-7d0aa8/"}],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"signal:who-serves-an-open-model-now-matters-as-much-as-which-model-you-pick-4a5cc7","retrieval_nugget":"3× between providers serving the same open-weight model on agent tasks, and the model makers' own APIs were neither the cheapest nor the fastest. Google Cloud reports up to 5x higher performance for Beam depending on the serving stack, and vLLM shows rack-scale tuning for DeepSeek.","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/signals/who-serves-an-open-model-now-matters-as-much-as-which-model-you-pick-4a5cc7/","markdown":"https://newruntime.com/signals/who-serves-an-open-model-now-matters-as-much-as-which-model-you-pick-4a5cc7.md","json":"https://newruntime.com/signals/who-serves-an-open-model-now-matters-as-much-as-which-model-you-pick-4a5cc7.json"},"next_reads":[{"type":"topic","path":"/topics/google/","url":"https://newruntime.com/topics/google/","title":"Google","reason":"Explore the google topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/google.md","json_url":"https://newruntime.com/topics/google.json"},{"type":"collection","path":"/signals/","url":"https://newruntime.com/signals/","title":"Raw Signals","reason":"Open every source-linked raw signal.","media_type":"text/html","json_url":"https://newruntime.com/signals.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}