gemini-2.5-pro vs mistral-large-3
Google Gemini against Mistral, priced on the same four workloads with price book 2026-10-22.
On real workloads
| Workload | gemini-2.5-pro per call | mistral-large-3 per call | Monthly difference |
|---|---|---|---|
| Chat reply 1,500 input and 400 output tokens, 100,000 calls a month |
$0.00588 | $0.00135 | −$452.50 |
| RAG answer, cached context 2,000 fresh + 4,000 cached input, 500 output, 100,000 calls a month |
$0.008 | $0.00195 | −$605.00 |
| Agent step 4,000 fresh + 8,000 cached input, 800 output, 250,000 calls a month |
$0.01 | $0.0036 | −$2,600.00 |
| Batch summary 3,000 input and 300 output tokens via the Batch API, 1,000,000 calls a month |
$0.00337 | — | — |
Monthly difference is mistral-large-3 minus gemini-2.5-pro. Batch rows use each provider's Batch API rates where published. Price both on your own workload.
Rates
| Model | Input | Output | Cache read | Cache write | Context |
|---|---|---|---|---|---|
| google/gemini-2.5-pro | $1.25 | $10.00 | $0.125 | — | 1M |
| mistral/mistral-large-3 | $0.50 | $1.50 | $0.05 | — | 262.1K |
Price is one input. Before switching, run your own prompts through both and compare quality; then veqen diff prices the change at your production volume.