Simulating realistic Document summarization parameters (25,000 in / 600 out with 10% cache reuse). Devstral 2 (2512) (OpenRouter) delivers a 87% cost reduction over Perplexity Sonar Pro.
| Traffic Volume Tier | Perplexity Sonar Pro Monthly | Devstral 2 (2512) (OpenRouter) Monthly | Monthly Savings by picking Devstral 2 (2512) (OpenRouter) |
|---|---|---|---|
| 1,000 reqs/mo (Dev/Testing) | $84.00 | $11.33 | Save $72.67 / mo |
| 10,000 reqs/mo (Small App) | $840.00 | $113.30 | Save $726.70 / mo |
| 100,000 reqs/mo (Growth Production) | $8,400.00 | $1,133.00 | Save $7,267.00 / mo |
| 1,000,000 reqs/mo (Scale SaaS) | $84,000.00 | $11,330.00 | Save $72,670.00 / mo |
Devstral 2 (2512) (OpenRouter) is 87% cheaper for Document summarization workloads. At standard Document summarization parameter ratios (25,000 input tokens, 600 output tokens, 10% cache hit), Devstral 2 (2512) (OpenRouter) costs $0.0113 per request compared to $0.084 on Perplexity Sonar Pro.
Perplexity Sonar Pro offers a context window of 200,000 tokens (max output: 8,192), while Devstral 2 (2512) (OpenRouter) offers 262,144 tokens (max output: 209,715).
At 100,000 requests per month, using Devstral 2 (2512) (OpenRouter) saves $7,267.00 every month (or $87,204.00 annually) compared to Perplexity Sonar 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.