Compare/Kimi K2 0905 vs Nova 2.0 Omni (medium)

Kimi K2 0905vsNova 2.0 Omni (medium)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Kimi

Kimi K2 0905

Input
$0.6/M
Output
$2.5/M
Speed
19 tok/s
TTFT
1.83s
Amazon

Nova 2.0 Omni (medium)

Input
$0.3/M
Output
$2.5/M
Speed
TTFT

Winner by Category

Cheaper
Nova 2.0 Omni (medium)
Faster (tok/s)
Kimi K2 0905
Lower Latency
Nova 2.0 Omni (medium)
Benchmarks (5-6)
Nova 2.0 Omni (medium)

Pricing Comparison

MetricKimi K2 0905Nova 2.0 Omni (medium)
Input ($/M tokens)$0.6$0.3
Output ($/M tokens)$2.5$2.5
Cost for 1M input + 100K output tokens:
Kimi K2 0905$0.85
Nova 2.0 Omni (medium)$0.55

Speed Comparison

Output Speed (tokens/s) — higher is better
Kimi K2 0905
19 tok/s
Nova 2.0 Omni (medium)
Time to First Token (seconds) — lower is better
Kimi K2 0905
1.83s
Nova 2.0 Omni (medium)

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
30.928.0
Coding Index
25.915.1
Math Index
57.389.7
GPQA Diamond
76.7%76.0%
MMLU-Pro
81.9%80.9%
LiveCodeBench
61.0%66.0%
AIME 2025
57.3%89.7%
MATH-500
Humanity's Last Exam
6.3%6.8%
SciCode
30.7%36.2%
IFBench
41.7%66.2%
TerminalBench
23.5%4.5%
Kimi K2 09055 wins
6 winsNova 2.0 Omni (medium)

Frequently Asked Questions

Which is cheaper, Kimi K2 0905 or Nova 2.0 Omni (medium)?

Nova 2.0 Omni (medium) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.85/M tokens vs $1.07/M for Kimi K2 0905.

Which model performs better on benchmarks?

Nova 2.0 Omni (medium) wins 6 out of 12 benchmarks compared to 5 for Kimi K2 0905. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Kimi K2 0905 generates tokens faster at 19 tok/s vs 0 tok/s. However, Nova 2.0 Omni (medium) has lower time-to-first-token (0.00s vs 1.83s).

When should I use Kimi K2 0905 vs Nova 2.0 Omni (medium)?

Choose based on your priorities: Nova 2.0 Omni (medium) for lower cost, Nova 2.0 Omni (medium) for stronger benchmark performance, and Kimi K2 0905 for faster generation. For latency-sensitive apps, check the TTFT comparison above.