Model comparison · text
Kimi-K2-Thinking vs Kimi-K2.5
Symmetrical, primary-source facts with unknown values left visible. No winner is assigned without comparable measurements.
FieldAt a glance
Moonshot AI · activeKimi-K2-ThinkingVerified Aug 28, 2026
Moonshot AI · activeKimi-K2.5Verified Aug 28, 2026
Technical differences
Side-by-side facts
| Field | Kimi-K2-Thinking | Kimi-K2.5 |
|---|---|---|
| Developer | Moonshot AI | Moonshot AI |
| Family | Kimi K2 Thinking | Kimi K2 5 |
| Model | Kimi-K2-Thinking | Kimi-K2.5 |
| Version | Kimi-K2-Thinking | Kimi-K2.5 |
| Lifecycle | active | active |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
| Context window | 262144 | 262144 |
| Total parameters | 1026408240256 | 1026879376368 |
| Active parameters | 32000000000 | 32000000000 |
| License | other | other |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Capabilities | chat, generation, reasoning, tools | chat, generation, reasoning, tools |
15 comparable fields · 5 material differences · Pair passes the primary-source comparison gate
Primary benchmark evidence
Comparable performance
No protocol-matched benchmark yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.
Kimi-K2-Thinking capabilities
Input price$0.60
Output price$2.50
Serving providers1
Canonical IDmoonshotai/Kimi-K2-Thinking
Kimi-K2.5 capabilities
Input price$0.60
Output price$3.00
Serving providers1
Canonical IDmoonshotai/Kimi-K2.5
Internal comparison graph
Related comparisons
Primary evidence