Simulating realistic Document summarization parameters (25,000 in / 600 out with 10% cache reuse). Kimi K2.7 Code (OpenRouter) delivers a 64% cost reduction over GPT-5.3 Codex.
| Traffic Volume Tier | GPT-5.3 Codex Monthly | Kimi K2.7 Code (OpenRouter) Monthly | Monthly Savings by picking Kimi K2.7 Code (OpenRouter) |
|---|---|---|---|
| 1,000 reqs/mo (Dev/Testing) | $48.213 | $17.59 | Save $30.623 / mo |
| 10,000 reqs/mo (Small App) | $482.125 | $175.90 | Save $306.225 / mo |
| 100,000 reqs/mo (Growth Production) | $4,821.25 | $1,759.00 | Save $3,062.25 / mo |
| 1,000,000 reqs/mo (Scale SaaS) | $48,212.50 | $17,590.00 | Save $30,622.50 / mo |
Kimi K2.7 Code (OpenRouter) is 64% cheaper for Document summarization workloads. At standard Document summarization parameter ratios (25,000 input tokens, 600 output tokens, 10% cache hit), Kimi K2.7 Code (OpenRouter) costs $0.0176 per request compared to $0.0482 on GPT-5.3 Codex.
GPT-5.3 Codex offers a context window of 256,000 tokens (max output: 64,000), while Kimi K2.7 Code (OpenRouter) offers 262,144 tokens (max output: 235,929).
At 100,000 requests per month, using Kimi K2.7 Code (OpenRouter) saves $3,062.25 every month (or $36,747.00 annually) compared to GPT-5.3 Codex.
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.