Skip to main content

Kimi K3 vs Kimi K3.1 Pro

SpecKimi K3Kimi K3.1 Pro
Respan Index52.8 (#35)71.4 (#9)
Blended price per 1M$2.52$1.94
Context window1.0M1.0M
Input / output per 1M$0.192 / $9.5$0.253 / $7
Max output1.0M1.0M
Inputtext, visiontext, vision, video
Released2026-07-162026-10-23

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryKimi K3Kimi K3.1 Pro
Coding38.8 Kimi K368.7 Kimi K3.1 Pro
Agents61.8 Kimi K370.3 Kimi K3.1 Pro
Reasoning54.8 Kimi K382.7* Kimi K3.1 Pro
Knowledge & language52.9 Kimi K372.2* Kimi K3.1 Pro
Human preference57.7 Kimi K358.3 Kimi K3.1 Pro

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

Kimi K3.1 Pro leads on 4 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkKimi K3Kimi K3.1 Pro
LMArena Elo14881482
LMArena WebDev (LMArena)16581683
LMArena Agent (LMArena)-0.00150.0388
APEX-Agents (Mercor)47.8%65.5%
Terminal-Bench 4.0 (Vals AI)17.2%63.6%

FAQ

Is Kimi K3 better than Kimi K3.1 Pro?

Kimi K3.1 Pro scores 71.4 on the Respan Index (#9), ahead of Kimi K3 at 52.8 (#35). Kimi K3.1 Pro leads on 4 of the 5 benchmarks both report.

Which is cheaper, Kimi K3 or Kimi K3.1 Pro?

Kimi K3 lists at $0.192 input and $9.5 output per 1M tokens; Kimi K3.1 Pro at $0.253 and $7. Kimi K3.1 Pro is 1.3x cheaper per token at list price.

Which has the larger context window?

Both accept 1.0M tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.