Simulating realistic Document summarization parameters (25,000 in / 600 out with 10% cache reuse). Databricks DBRX Instruct delivers a 35% cost reduction over GLM-5 (Z.ai).
| Traffic Volume Tier | GLM-5 (Z.ai) Monthly | Databricks DBRX Instruct Monthly | Monthly Savings by picking Databricks DBRX Instruct |
|---|---|---|---|
| 1,000 reqs/mo (Dev/Testing) | $24.92 | $16.08 | Save $8.84 / mo |
| 10,000 reqs/mo (Small App) | $249.20 | $160.80 | Save $88.40 / mo |
| 100,000 reqs/mo (Growth Production) | $2,492.00 | $1,608.00 | Save $884.00 / mo |
| 1,000,000 reqs/mo (Scale SaaS) | $24,920.00 | $16,080.00 | Save $8,840.00 / mo |
Databricks DBRX Instruct is 35% cheaper for Document summarization workloads. At standard Document summarization parameter ratios (25,000 input tokens, 600 output tokens, 10% cache hit), Databricks DBRX Instruct costs $0.0161 per request compared to $0.0249 on GLM-5 (Z.ai).
GLM-5 (Z.ai) offers a context window of 200,000 tokens (max output: 131,072), while Databricks DBRX Instruct offers 32,768 tokens (max output: 4,096).
At 100,000 requests per month, using Databricks DBRX Instruct saves $884.00 every month (or $10,608.00 annually) compared to GLM-5 (Z.ai).
Long-context models pay off here — compare price per 1M tokens at your true document size. Summarize once, store the result; don't re-summarize unchanged documents. For batch backfills, nightly jobs can use cache-friendly request ordering.