// head_to_head
Kimi K3 vs Pareto 26.9
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.
Kimi K3 and Pareto 26.9 are priced within ~10% of each other.
Pareto 26.9 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.
moonshotai
Kimi K3
- Blended / 1M
- $3.90
- Context
- 1.0M
- Released
- Jul 16, 2026
- Overall score
- 63.4
unbiased
Pareto 26.9
- Blended / 1M
- $3.75
- Context
- 262K
- Released
- Oct 13, 2026
- Overall score
- Not evaluated
Specs and pricing
| Metric | Kimi K3 | Pareto 26.9 |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 63.4 | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $1.24 | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $3.90 | $3.75 |
| Input price / 1M | $0.700win | $2.50 |
| Output price / 1M | $13.50 | $7.50win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.280 | $0.250win |
| Context window | 1.0Mwin | 262K |
| Max output tokens | 944Kwin | 131K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Kimi K3 on top, Pareto 26.9 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 | Kimi K3 | Pareto 26.9 |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $1,218/mo | $1,038/mo |
| RAG assistant 8K in / 600 out × 100K requests | $1,202/mo | $1,550/mo |
| Coding agent 40K in / 4K out × 20K requests | $1,405/mo | $1,340/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $1,692/mo | $2,950/mo |
| Bulk classification 500 in / 20 out × 5M requests | $2,890/mo | $5,875/mo |
Which should you pick?
You need to fit large documents in one call
Kimi K3
Wider context window — 1.0M against 262K.
Kimi K3 vs Pareto 26.9 FAQ
Which is better, Kimi K3 or Pareto 26.9?
Kimi K3 and Pareto 26.9 are priced within ~10% of each other. Pareto 26.9 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 Kimi K3 cheaper than Pareto 26.9?
They cost about the same. Both land near $3.90 per million tokens on a 3:1 input:output blend, so price is unlikely to be the deciding factor between them.
Does Kimi K3 or Pareto 26.9 have a bigger context window?
Kimi K3 has the larger context window: 1.0M for Kimi K3 against 262K for Pareto 26.9. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.
Do Kimi K3 and Pareto 26.9 support prompt caching?
Both publish a cached-input rate: $0.280 per million for Kimi K3 and $0.250 for Pareto 26.9, against full input rates of $0.700 and $2.50. 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 2026-09-02, 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.