// head_to_head
Kimi K3 vs Kimi K3.1 Pro
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 K3.1 Pro scores higher, Kimi K3 costs less — it depends on your workload.
Kimi K3.1 Pro is ahead by 6.7 points overall, and Kimi K3 lists 34% cheaper per blended million tokens. Whether 6.7 points is worth that depends on how much a wrong answer costs you. The two cost measures disagree here, which is worth knowing: Kimi K3 has the lower sticker price, but Kimi K3.1 Pro earns each point of capability for less — $0.0104 against $0.0219 — because per-token rates do not predict how many tokens a model actually spends on a task.
moonshotai
Kimi K3
- Blended / 1M
- $2.99
- Context
- 1.0M
- Released
- Jul 16, 2026
- Overall score
- 64.6
moonshotai
Kimi K3.1 Pro
- Blended / 1M
- $4.00
- Context
- 1.0M
- Released
- Oct 23, 2026
- Overall score
- 71.3
Specs and pricing
| Metric | Kimi K3 | Kimi K3.1 Pro |
|---|---|---|
| LiveBench overall Weighted mean of the seven LiveBench category scores, 0–100. Higher is better. | 64.6 | 71.3win |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0219 | $0.0104win |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $2.99win | $4.00 |
| Input price / 1M | $0.159win | $2.00 |
| Output price / 1M | $11.50 | $10.00win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.149win | $0.200 |
| Context window | 1.0M | 1.0M |
| Max output tokens | 944K | 944K |
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, Kimi K3.1 Pro 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 | Kimi K3.1 Pro |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $957.44/mo | $1,150/mo |
| RAG assistant 8K in / 600 out × 100K requests | $813.20/mo | $1,480/mo |
| Coding agent 40K in / 4K out × 20K requests | $1,042/mo | $1,392/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $1,021/mo | $2,660/mo |
| Bulk classification 500 in / 20 out × 5M requests | $1,543/mo | $5,100/mo |
Which should you pick?
You are running this at volume
Kimi K3.1 Pro
Lowest measured cost per point of capability at $0.0104 per point — the gap compounds with every request.
Quality matters more than the bill
Kimi K3.1 Pro
Highest overall LiveBench score of the two at 71.3.
The workload is coding or agentic work
Kimi K3.1 Pro
Leads on long-horizon agentic — 39.1 against 26.4.
You are cost-constrained
Kimi K3
Cheaper on blended list price at $2.99 per million tokens.
Kimi K3 vs Kimi K3.1 Pro FAQ
Which is better, Kimi K3 or Kimi K3.1 Pro?
Kimi K3.1 Pro scores higher, Kimi K3 costs less — it depends on your workload. Kimi K3.1 Pro is ahead by 6.7 points overall, and Kimi K3 lists 34% cheaper per blended million tokens. Whether 6.7 points is worth that depends on how much a wrong answer costs you. The two cost measures disagree here, which is worth knowing: Kimi K3 has the lower sticker price, but Kimi K3.1 Pro earns each point of capability for less — $0.0104 against $0.0219 — because per-token rates do not predict how many tokens a model actually spends on a task.
Is Kimi K3 cheaper than Kimi K3.1 Pro?
Kimi K3 is cheaper. On a 3:1 input:output blend, Kimi K3 lists at $2.99 per million tokens and Kimi K3.1 Pro at $4.00 — Kimi K3 is 34% cheaper. Input and output are priced separately — Kimi K3 charges $0.159 in and $11.50 out, Kimi K3.1 Pro charges $2.00 and $10.00 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Kimi K3 vs Kimi K3.1 Pro: which scores higher on benchmarks?
Kimi K3 scores 64.6 and Kimi K3.1 Pro scores 71.3 overall on LiveBench, the weighted mean of its seven categories. That is a 6.7-point lead for Kimi K3.1 Pro. Category scores differ from the overall figure — a model can lead on reasoning and trail on coding, which the per-category table above breaks out.
Which gives better value for money, Kimi K3 or Kimi K3.1 Pro?
Kimi K3.1 Pro. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. Kimi K3 works out at $0.0219 per point and Kimi K3.1 Pro at $0.0104.
Does Kimi K3 or Kimi K3.1 Pro have a bigger context window?
They are effectively the same — 1.0M for Kimi K3 and 1.0M for Kimi K3.1 Pro.
Do Kimi K3 and Kimi K3.1 Pro support prompt caching?
Both publish a cached-input rate: $0.149 per million for Kimi K3 and $0.200 for Kimi K3.1 Pro, against full input rates of $0.159 and $2.00. 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 2026-10-25, 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.