Coding model for repository understanding, refactors, and agentic engineering tasks
KAT-Coder-Pro-V2 by kuaishou is currently listed from a single provider. Its reference price is $0.30 per 1M input tokens and $1.20 per 1M output tokens.
Artificial Analysis rates it 21.7 on the Intelligence Index, with 59.5 for coding. Against its lowest blended price of $0.525 per 1M, that is roughly 41 index points per dollar, which is the value ratio the leaderboards rank on.
The context window is 256,000 tokens, with an output limit of 80,000 tokens. It supports tool use.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| ZenMux | Gateway | $0.30 | $1.20 | $0.06 | — | 256,000 | 80,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-23). Each future sync adds a point, and once accumulated a line is drawn here.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.