Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Jamba 1.6 Large | Mistral Medium |
|---|---|---|
| Input ($/M tokens) | $2 | $2.75 |
| Output ($/M tokens) | $8 | $8.1 |
Data from Artificial Analysis API — 12 benchmarks
Jamba 1.6 Large is cheaper overall. Its blended price (3:1 input/output ratio) is $3.50/M tokens vs $4.09/M for Mistral Medium.
Jamba 1.6 Large wins 7 out of 12 benchmarks compared to 0 for Mistral Medium. See the detailed benchmark chart above for per-category results.
Mistral Medium generates tokens faster at 73 tok/s vs 59 tok/s. However, Mistral Medium has lower time-to-first-token (0.40s vs 0.73s).
Choose based on your priorities: Jamba 1.6 Large for lower cost, Jamba 1.6 Large for stronger benchmark performance, and Mistral Medium for faster generation. For latency-sensitive apps, check the TTFT comparison above.