Model comparison · embedding, image, text
Kimi-K2.5 vs Kimi-K3
Symmetrical, primary-source facts with unknown values left visible. No winner is assigned without comparable measurements.
Technical differences
Side-by-side facts
| Field | Kimi-K2.5 | Kimi-K3 |
|---|---|---|
| Developer | Moonshot AI | Moonshot AI |
| Family | Kimi K2 5 | Kimi K3 |
| Model | Kimi-K2.5 | Kimi-K3 |
| Version | Kimi-K2.5 | Kimi-K3 |
| Lifecycle | active | active |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
| Context window | 262144 | 1048576 |
| Total parameters | 1026879376368 | 2779931837184 |
| Active parameters | 32000000000 | 104000000000 |
| License | other | other |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Capabilities | chat, generation, reasoning, tools | chat, generation, reasoning |
15 comparable fields · 7 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-K2.5 capabilities
Input price$0.60
Output price$3.00
Serving providers1
Canonical IDmoonshotai/Kimi-K2.5
Kimi-K3 capabilities
Input price$3.00
Output price$15.00
Serving providers1
Canonical IDmoonshotai/Kimi-K3
Internal comparison graph
Related comparisons
Primary evidence