Simulating realistic Document summarization parameters (25,000 in / 600 out with 10% cache reuse). Pixtral Large delivers a 7% cost reduction over Gemini 3.1 Pro.
| Traffic Volume Tier | Gemini 3.1 Pro Monthly | Pixtral Large Monthly | Monthly Savings by picking Pixtral Large |
|---|---|---|---|
| 1,000 reqs/mo (Dev/Testing) | $52.70 | $49.10 | Save $3.60 / mo |
| 10,000 reqs/mo (Small App) | $527.00 | $491.00 | Save $36.00 / mo |
| 100,000 reqs/mo (Growth Production) | $5,270.00 | $4,910.00 | Save $360.00 / mo |
| 1,000,000 reqs/mo (Scale SaaS) | $52,700.00 | $49,100.00 | Save $3,600.00 / mo |
Pixtral Large is 7% cheaper for Document summarization workloads. At standard Document summarization parameter ratios (25,000 input tokens, 600 output tokens, 10% cache hit), Pixtral Large costs $0.0491 per request compared to $0.0527 on Gemini 3.1 Pro.
Gemini 3.1 Pro offers a context window of 2,000,000 tokens (max output: 128,000), while Pixtral Large offers 128,000 tokens (max output: 8,192).
At 100,000 requests per month, using Pixtral Large saves $360.00 every month (or $4,320.00 annually) compared to Gemini 3.1 Pro.
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.