// head_to_head
KAT-Coder-Pro V2.5 vs Kimi K2.7 Code
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
KAT-Coder-Pro V2.5 and Kimi K2.7 Code are priced within ~10% of each other.
KAT-Coder-Pro V2.5 does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
kwaipilot
KAT-Coder-Pro V2.5
- Blended / 1M
- $1.29
- Context
- 262K
- Released
- Jul 10, 2026
- Overall score
- Not evaluated
moonshotai
Kimi K2.7 Code
- Blended / 1M
- $1.35
- Context
- 262K
- Released
- Jun 12, 2026
- Overall score
- 68.4
Specs and pricing
| Metric | KAT-Coder-Pro V2.5 | Kimi K2.7 Code |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | — | 68.4 |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | — | $0.0545 |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $1.29 | $1.35 |
| Input price / 1M | $0.740 | $0.706 |
| Output price / 1M | $2.96win | $3.30 |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.150win | $0.180 |
| Context window | 262K | 262K |
| Max output tokens | 236K | 236K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — KAT-Coder-Pro V2.5 on top, Kimi K2.7 Code below, both out of 100.
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | KAT-Coder-Pro V2.5 | Kimi K2.7 Code |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $371.92/mo | $395.60/mo |
| RAG assistant 8K in / 600 out × 100K requests | $533.60/mo | $552.48/mo |
| Coding agent 40K in / 4K out × 20K requests | $498.40/mo | $534.29/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $932.50/mo | $927.39/mo |
| Bulk classification 500 in / 20 out × 5M requests | $1,851/mo | $1,832/mo |
KAT-Coder-Pro V2.5 vs Kimi K2.7 Code FAQ
Which is better, KAT-Coder-Pro V2.5 or Kimi K2.7 Code?
KAT-Coder-Pro V2.5 and Kimi K2.7 Code are priced within ~10% of each other. KAT-Coder-Pro V2.5 does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
Is KAT-Coder-Pro V2.5 cheaper than Kimi K2.7 Code?
They cost about the same. Both land near $1.29 per million tokens on a 3:1 input:output blend, so price is unlikely to be the deciding factor between them.
Does KAT-Coder-Pro V2.5 or Kimi K2.7 Code have a bigger context window?
They are effectively the same — 262K for KAT-Coder-Pro V2.5 and 262K for Kimi K2.7 Code.
Do KAT-Coder-Pro V2.5 and Kimi K2.7 Code support prompt caching?
Both publish a cached-input rate: $0.150 per million for KAT-Coder-Pro V2.5 and $0.180 for Kimi K2.7 Code, against full input rates of $0.740 and $0.706. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.