Simulating realistic Document summarization parameters (25,000 in / 600 out with 10% cache reuse). Mistral Large 3 delivers a 62% cost reduction over DeepSeek V4 Pro.
| Traffic Volume Tier | DeepSeek V4 Pro Monthly | Mistral Large 3 Monthly | Monthly Savings by picking Mistral Large 3 |
|---|---|---|---|
| 1,000 reqs/mo (Dev/Testing) | $32.186 | $12.275 | Save $19.911 / mo |
| 10,000 reqs/mo (Small App) | $321.86 | $122.75 | Save $199.11 / mo |
| 100,000 reqs/mo (Growth Production) | $3,218.60 | $1,227.50 | Save $1,991.10 / mo |
| 1,000,000 reqs/mo (Scale SaaS) | $32,186.00 | $12,275.00 | Save $19,911.00 / mo |
Mistral Large 3 is 62% cheaper for Document summarization workloads. At standard Document summarization parameter ratios (25,000 input tokens, 600 output tokens, 10% cache hit), Mistral Large 3 costs $0.0123 per request compared to $0.0322 on DeepSeek V4 Pro.
DeepSeek V4 Pro offers a context window of 1,000,000 tokens (max output: 384,000), while Mistral Large 3 offers 1,000,000 tokens (max output: 64,000).
At 100,000 requests per month, using Mistral Large 3 saves $1,991.10 every month (or $23,893.20 annually) compared to DeepSeek V4 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.