Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Kimi K2 Thinking | Grok 4.3 (medium) |
|---|---|---|
| Input ($/M tokens) | $0.6 | $1.25 |
| Output ($/M tokens) | $2.5 | $2.5 |
Data from Artificial Analysis API — 12 benchmarks
Kimi K2 Thinking is cheaper overall. Its blended price (3:1 input/output ratio) is $1.07/M tokens vs $1.56/M for Grok 4.3 (medium).
It's a tie — both models win 5 benchmarks each across 12 evaluated categories. See the detailed benchmark chart above for per-category results.
Kimi K2 Thinking generates tokens faster at 168 tok/s vs 103 tok/s. Kimi K2 Thinking also has lower time-to-first-token (0.78s vs 21.73s).
Choose based on your priorities: Kimi K2 Thinking for lower cost, both perform similarly on benchmarks, and Kimi K2 Thinking for faster generation. For latency-sensitive apps, check the TTFT comparison above.