DeepSeek R1 vs Kimi K2.7 Code: cost comparison
Prices updated 2026-10-28 · computed from live provider data
Short answer: DeepSeek R1 is cheaper on a
3:1 input/output blend — $0.960 per million tokens versus
$1.20, a 20% difference.
Kimi K2.7 Code offers the larger context window at 262,144 tokens, against 65,536 for DeepSeek R1.
Head to head
| DeepSeek R1 | Kimi K2.7 Code | |
|---|---|---|
| Input, per 1M tokens | $0.550 | $0.560 |
| Output, per 1M tokens | $2.19 | $3.10 |
| Blended 3:1, per 1M | $0.960 | $1.20 |
| Context window | 65,536 | 262,144 |
| Vendor | deepseek | moonshotai |
Monthly cost at real volumes
| Workload (input / output) | DeepSeek R1 | Kimi K2.7 Code |
|---|---|---|
| 1M in / 250K out | $1.10 | $1.33 |
| 10M in / 2.5M out | $10.97 | $13.35 |
| 100M in / 25M out | $110 | $134 |
Which should you pick?
Pick Kimi K2.7 Code when you need the longer context window (262,144 vs 65,536 tokens). Pick DeepSeek R1 when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.