Model comparison
Kimi K2 0905 vs Kimi K2.5
Compare Kimi K2 0905 and Kimi K2.5: input/output $/Mtoken, context window, modalities, and license. OpenRouter-synced pricing.
Moonshotai
Kimi K2 0905
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trilli
Moonshotai
Kimi K2.5
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued p
| Metric | Kimi K2 0905 | Kimi K2.5 |
|---|---|---|
| Provider | Moonshotai | Moonshotai |
| Context window | 262,144 | 262,144 |
| Input $/Mtok | $0.600 | $0.375 |
| Output $/Mtok | $2.50 | $2.02 |
| Modalities | text | text, vision |
| License | open-weights | open-weights |
Quick take
On input price, Kimi K2.5 is cheaper at $0.375/Mtok. For context window, Kimi K2 0905 leads with 262,144 tokens.
Pick based on your workload: high-volume cheap inference vs long-document / agent loops. Enterprise DNA can wire either model into Omni with evals, secrets, and job orchestration.