From 9c493454a5ec2a611a1a07602ae130936a3dffb9 Mon Sep 17 00:00:00 2001 From: Andrey Cheptsov Date: Wed, 11 Nov 2026 17:14:33 +0100 Subject: [PATCH] Drop the cost percentage claims from the GLM-5.3 post The description, intro, and conclusion now say that self-hosting costs less than buying the same tokens, without the 70% and under-a-third figures. Dollar figures stay next to their SemiAnalysis source. Co-Authored-By: Claude Opus 5.5 --- mkdocs/blog/posts/glm53-gb200-nvl72-coding-agents.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mkdocs/blog/posts/glm53-gb200-nvl72-coding-agents.md b/mkdocs/blog/posts/glm53-gb200-nvl72-coding-agents.md index 761ddcf27..ce82c2219 100644 --- a/mkdocs/blog/posts/glm53-gb200-nvl72-coding-agents.md +++ b/mkdocs/blog/posts/glm53-gb200-nvl72-coding-agents.md @@ -1,7 +1,7 @@ --- title: "Serve GLM-5.3 Coding Agents Faster and Cheaper on GB200 NVL72" date: 2026-11-10 -description: "Optimized with dstack presets, 14 GB200 NVL72 nodes serve 48 GLM-5.3 coding agents as fast as the three fastest OpenRouter endpoints, with lower p50 TTFT, and self-hosting them costs under a third of buying the same tokens." +description: "Optimized with dstack presets, 14 GB200 NVL72 nodes serve 48 GLM-5.3 coding agents as fast as the three fastest OpenRouter endpoints, with lower p50 TTFT, and self-hosting them costs less than buying the same tokens." slug: glm53-gb200-nvl72-coding-agents unlisted: true image: https://dstack.ai/static-assets/static-assets/images/dstack-glm-53-gb200-nvl72-crusoe.png @@ -11,7 +11,7 @@ categories: # Serve GLM-5.3 Coding Agents Faster and Cheaper on GB200 NVL72 -With `dstack` [presets](../../docs/concepts/presets.md), the preset agent optimized a GB200 NVL72 fleet to serve GLM-5.3 coding agents as fast as the three fastest endpoints on OpenRouter, with lower p50 TTFT. Self-hosting them this way costs under a third of buying the same tokens from those endpoints. By a coding agent we mean one session of a tool like Claude Code: a multi-turn conversation that resends its whole context, about 135k tokens, on every request and spawns subagents along the way. +With `dstack` [presets](../../docs/concepts/presets.md), the preset agent optimized a GB200 NVL72 fleet to serve GLM-5.3 coding agents as fast as the three fastest endpoints on OpenRouter, with lower p50 TTFT. Self-hosting them this way costs less than buying the same tokens from those endpoints. By a coding agent we mean one session of a tool like Claude Code: a multi-turn conversation that resends its whole context, about 135k tokens, on every request and spawns subagents along the way. @@ -108,7 +108,7 @@ We then raised the agent count for each winner. Aggregated, replayed at normal p ### Self-hosting is economically viable -Optimized for 48 agents, 14 GB200 nodes match the fastest GLM-5.3 endpoints on p50 output speed and beat them on p50 TTFT and on output speed at p99. Self-hosting costs $12.77 per million output tokens, at least 70% less than the $43–66 it costs to buy the same tokens from these endpoints. +Optimized for 48 agents, 14 GB200 nodes match the fastest GLM-5.3 endpoints on p50 output speed and beat them on p50 TTFT and on output speed at p99. Self-hosting them costs less than buying the same tokens from these endpoints, even on GB200 NVL72 and without patching the engine or writing kernels. ### Cache fit decides aggregated vs PD