← Models

Kimi K3 vs Kimi K3.1 Pro

Compare Kimi K3 from Moonshot AI and Kimi K3.1 Pro from Moonshot AI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.

Moonshot AIKimi K3Moonshot AIKimi K3.1 Pro
Moonshot AI logo
Kimi K3
Moonshot AI · text, image, video → text

Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window and industry-leading intelligence.

Input$2.84 /M
Output$14.2 /M
Cache read$0.284 /M
10% off·Nov 9 09:00 – Nov 23 09:00 GMT+0
Moonshot AI logo
Kimi K3.1 Pro
Moonshot AI · text, image, video → text

Kimi K3.1 Pro is based on Moonshot AI’s Kimi K3.1, offering code generation and interactive content development capabilities for coding assistance, code analysis, and visual prototyping.

Input$2$1.8 /M
Output$10$9 /M
Cache read$0.2$0.18 /M

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

Kimi K3
Kimi K3.1 Pro
Input
$2.84 /M
$2$1.8 /M−10%
Output
$14.2 /M
$10$9 /M−10%
Cache read
$0.284 /M
$0.2$0.18 /M−10%
Context length
1,048,576
1,048,576
Max output
1,048,576
1,048,576
Time to First Token
0.6 s
0.9 s
Throughput
73.1 tok/s
90.4 tok/s
Modalities
textimagevideo
textimagevideo
Supported Parameters
thinkingfunction callingstructured outputs
API Formats
Released
July 16, 2026
October 24, 2026

Promotional prices show the discounted rate; see each model page for promotion windows.

Activity Past 30 Days

Daily traffic served through AIHubMix — how demand for each model is trending.

kimi-k3kimi-k3.1-pro

Tokens / day

-

Requests / day

-

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

kimi-k3kimi-k3.1-pro

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.

Text
kimi-k3kimi-k3.1-pro
1440148015201560
Overall
14831487
Coding
15261537
Math
15031503
Hard prompts
15011515
Instruction following
14851488
Multi-turn
14731501
Creative writing
14571459
Longer query
14881500
Chinese
15381540
English
14921493
WebDev Arena
kimi-k3kimi-k3.1-pro
1560162016801740
Overall
16581688
React
16721700
HTML
16411689
Gaming
17041737
Simulations
16851738
Data analytics
15821594

Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.

Cost calculator

Estimate your monthly bill for the same workload on each model.

Kimi K3.1 Pro
$270$243 /mo
Kimi K3
$383 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

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

Kimi K3.1 Pro: $9/M output tokens; Kimi K3: $14.2/M. Use the cost calculator above to estimate your own workload.

How do their coding arena scores compare?

Kimi K3: 1537; Kimi K3.1 Pro: 1526 (LMArena coding leaderboard).

Which responds faster?

Kimi K3: 0.6s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.

How large is each context window?

Kimi K3 accepts 1,048,576 and Kimi K3.1 Pro accepts 1,048,576 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 1,048,576 tokens on Kimi K3.1 Pro.

Which one generates tokens faster?

Kimi K3.1 Pro at 90.4 tok/s and Kimi K3 at 73.1 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs; Kimi K3.1 Pro accepts text, image and video input.

Can I call Kimi K3 and Kimi K3.1 Pro with the same API key?

Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.

Popular comparisons

Related model match-ups readers also look at.