Skip to content
ModelCap

Head-to-head comparison

Kimi K3 vs Kimi K3.1 Pro

Kimi K3 (Moonshot AI) and Kimi K3.1 Pro (Moonshot AI) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 19 November 2026

As of 19 November 2026, Kimi K3.1 Pro holds the stronger ModelCap Index position (#11 vs #17); and Kimi K3.1 Pro is 1.8× cheaper per output token ($8.80/1M vs $16.00/1M).

Which should you choose?

Choose Kimi K3 if…

  • your workload is prompt-heavy — input tokens cost $0.192/1M against $0.253/1M.
  • Arena text is your yardstick — 1487 against 1487.

Choose Kimi K3.1 Pro if…

  • you want the stronger overall ModelCap Index position — #11 against #17 (80.0 vs 79.0 points).
  • API cost matters — $8.80/1M output tokens against $16.00/1M, about 1.8× cheaper.
  • Arena coding is your yardstick — 1537 against 1536.
  • LMArena Agent is your yardstick — 3.9% against -0.1%.
  • you want the more recently listed model — Kimi K3.1 Pro was listed 23 October 2026, Kimi K3 16 July 2026.

Kimi K3 vs Kimi K3.1 Pro: specs, pricing and context

Specification comparison of Kimi K3 and Kimi K3.1 Pro
FieldKimi K3Moonshot AIKimi K3.1 ProMoonshot AI
ModelCap Index position#17#11
Index score79.080.0
EvidenceMeasuredMeasured
Input price / 1M tokens$0.192$0.253
Output price / 1M tokens$16.00$8.80
Context window1M tokens1M tokens
Declared route output cap944K944K
API providers listed2020
Weight accessRestricted licenseRestricted license
Input modalitiesText, Image, VideoText, Image, Video
First listed16 July 202623 October 2026
PublisherMoonshot AIMoonshot AI

Evidence: 4 public benchmark observations across 4 boards · 3 public benchmark observations across 3 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Kimi K3 vs Kimi K3.1 Pro

Public benchmark boards where Kimi K3 or Kimi K3.1 Pro has a published result
BoardKimi K3Kimi K3.1 ProLeads
Arena textArena (LMArena)14871483–1491Max14871478–1495MaxKimi K3
Arena codingArena (LMArena)15361530–1543Max15371521–1554MaxKimi K3.1 Pro
LMArena AgentLMArena-0.1%-0.8%–0.5%Max3.9%2.8%–5.0%MaxKimi K3.1 Pro
ARC-AGI-2ARC Prize Foundation60.4%Max—Only one result
AA Intelligence IndexArtificial Analysis—46.5ReasoningOnly one result
WildClawBench OpenClawWildClawBench54.5—Only one result

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Kimi K3 vs Kimi K3.1 Pro: common questions

Is Kimi K3 better than Kimi K3.1 Pro?

Kimi K3.1 Pro ranks higher on the ModelCap Index as of 19 November 2026: #11 against #17. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.

Is Kimi K3 cheaper than Kimi K3.1 Pro?

Kimi K3.1 Pro is cheaper on output tokens: $8.80/1M against $16.00/1M. Input tokens are $0.192/1M for Kimi K3 and $0.253/1M for Kimi K3.1 Pro. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $8.38 for Kimi K3 versus $4.91 for Kimi K3.1 Pro. Kimi K3.1 Pro costs 41.5% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.

Which has the bigger context window, Kimi K3 or Kimi K3.1 Pro?

Both publish a 1M-token context window. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified.

Which is better for coding, Kimi K3 or Kimi K3.1 Pro?

Arena coding: Kimi K3 1536, Kimi K3.1 Pro 1537 — Kimi K3.1 Pro leads.

Are Kimi K3 and Kimi K3.1 Pro open-weight models?

Kimi K3: Restricted license. Kimi K3.1 Pro: Restricted license. Open weights mean the checkpoint can be downloaded and self-hosted under its licence. A missing weight link does not identify every API or chat product that offers a model.

Where can I run Kimi K3 and Kimi K3.1 Pro?

ModelCap currently lists 20 API providers for Kimi K3 and 20 for Kimi K3.1 Pro, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Kimi K3 vs Kimi K3.1 Pro comparison?

Every figure and ModelCap Index position comes from the same published snapshot dated 19 November 2026. Publication and page updates happen separately; use the snapshot date shown on the page.

Explore further