Moonshot AI Kimi
Kimi K2 Instruct
$0.875 / 1M tokens
cheapest at DeepInfra · $0.50 in · $2.00 out
Wins 1 of 3
Head to head · prices updated Nov 1, 2026
Kimi K2 Instruct costs 35.0× as much as deepseek-r1-distill-llama-8b at their cheapest providers (blended 3 input : 1 output tokens).
Moonshot AI Kimi
$0.875 / 1M tokens
cheapest at DeepInfra · $0.50 in · $2.00 out
Wins 1 of 3
DeepSeek
$0.025 / 1M tokens
cheapest at Nscale · $0.025 in · $0.025 out
Wins 1 of 3
Verdict
Kimi K2 Instruct costs 35.0× as much as deepseek-r1-distill-llama-8b at their cheapest providers (blended 3 input : 1 output tokens).
Your monthly bill
deepseek-r1-distill-llama-8b saves you $8.70 a month ($104.40 a year) for this workload.
| Kimi K2 Instruct | deepseek-r1-distill-llama-8b | |
|---|---|---|
| Cheapest blended price / 1M | $0.875 | $0.025 |
| Input / output per 1M | $0.50 / $2.00 | $0.025 / $0.025 |
| Accuracy (GPQA Diamond) | not measured | not measured |
| Max context | 131K | 131K |
| Providers we track | 4 | 2 |
Standard list prices at each model's cheapest provider we track; blended = 3 input : 1 output tokens. GPQA Diamond from Epoch AI (CC BY 4.0), best measured reasoning setting, named next to each score. Methodology.
Kimi K2 Instruct costs 35.0× as much as deepseek-r1-distill-llama-8b at their cheapest providers (blended 3 input : 1 output tokens).
From $0.50 input and $2.00 output per 1M tokens at DeepInfra, the cheapest of 4 providers we track.
From $0.025 input and $0.025 output per 1M tokens at Nscale, the cheapest of 2 providers we track.
Swap a model