Home › Compare › MoonshotAI: Kimi K2 Thinking vs MoonshotAI: Kimi K2.5
MoonshotAI: Kimi K2 Thinking vs MoonshotAI: Kimi K2.5: API Pricing Compared
Comparing MoonshotAI: Kimi K2 Thinking and MoonshotAI: Kimi K2.5: on combined input+output list price, MoonshotAI: Kimi K2.5 is cheaper at $3 vs $3.1 per 1M tokens — a difference of $0.1 (3%). MoonshotAI: Kimi K2 Thinking costs $0.6 in / $2.5 out with a 262,144-token context; MoonshotAI: Kimi K2.5 costs $0.5 in / $2.5 out with a 262,144-token context.
| MoonshotAI: Kimi K2 Thinking | MoonshotAI: Kimi K2.5 | |
|---|---|---|
| Input /1M | $0.6 | $0.5 |
| Output /1M | $2.5 | $2.5 |
| Cached input /1M | $0.15 | $0.15 |
| Context window | 262,144 | 262,144 |
| Max output tokens | 98,304 | 235,929 |
| Cost @ 10M in + 2M out / mo | $11 | $10 |
Estimate your own workload in the cost calculator, or open the full pages for MoonshotAI: Kimi K2 Thinking and MoonshotAI: Kimi K2.5.
Frequently asked questions
Which is cheaper, MoonshotAI: Kimi K2 Thinking or MoonshotAI: Kimi K2.5?
MoonshotAI: Kimi K2.5 is cheaper on combined list price: $3 vs $3.1 per 1M tokens (input + output). At 10M input + 2M output tokens per month, MoonshotAI: Kimi K2 Thinking costs $11 and MoonshotAI: Kimi K2.5 costs $10.
Which has the larger context window, MoonshotAI: Kimi K2 Thinking or MoonshotAI: Kimi K2.5?
MoonshotAI: Kimi K2 Thinking has a context window of 262,144 tokens; MoonshotAI: Kimi K2.5 has 262,144 tokens. The larger one is MoonshotAI: Kimi K2 Thinking.
Price snapshot October 21, 2026, refreshed daily.