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$3.00 /M
Output$15.00 /M
← ModelsKimi K3
MiMo V2 Pro
Kimi K3 vs MiMo V2 Pro
Output tokens cost $15.00 per million on Kimi K3 and $3.30 per million on MiMo V2 Pro. Input tokens cost $3.00 per million on Kimi K3 and $1.10 per million on MiMo V2 Pro. Cached input tokens are billed at $0.30 per million on Kimi K3 and $0.22 per million on MiMo V2 Pro. Context lengths are 1,048,576 tokens on Kimi K3 and 1,000,000 tokens on MiMo V2 Pro. Time to first token (TTFT) measured on AIHubMix is 0.9s on Kimi K3 and 1.7s on MiMo V2 Pro. Measured output throughput is 73.1 tok/s on Kimi K3 and 41.3 tok/s on MiMo V2 Pro. On the LMArena coding leaderboard Kimi K3 scores 1531 and MiMo V2 Pro scores 1503.
Kimi K3MiMo V2 Pro+ Add model · 2/4
MiMo V2 Pro
Xiaomi · text, image, video, audio → text
Xiaomi MiMo-V2-Pro is built for high-intensity agent work scenarios in the real world. It has over 1 trillion total parameters (42B active parameters), employs an innovative hybrid-attention architecture, and supports an ultra-long 1M-token context length. On top of a powerful model foundation, we continuously scale compute across broader agent scenarios, further expanding the intelligent action space and achieving significant generalization from Coding to Claw.
Input$1.10 /M
Output$3.30 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
MiMo V2 Pro
Input /M
$3.00
$1.10
Output /M
$15.00
$3.30
Cache read /M
$0.30
$0.22
Context length
1,048,576
1,000,000
Max output
1,048,576
0
Time to First Token
0.9 s
1.7 s
Throughput
73.1 tok/s
41.3 tok/s
Modalities
textimagevideo
textimagevideoaudio
Supported Parameters
thinkingfunction callingstructured outputs
web
API Formats
Released
-
-
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-k3mimo-v2-pro
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3mimo-v2-pro
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3mimo-v2-pro
14001440148015201560
Overall
14481486
Coding
15031531
Math
14521452
Hard prompts
14761505
Instruction following
14451479
Multi-turn
14701499
Creative writing
14251470
Longer query
14671502
Chinese
14831527
English
14651491
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.
MiMo V2 Pro
$116 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, MiMo V2 Pro?
MiMo V2 Pro: $3.30/M output tokens; Kimi K3: $15.00/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
Kimi K3: 1531; MiMo V2 Pro: 1503 (LMArena coding leaderboard).
Which responds faster?
Kimi K3: 0.9s 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 MiMo V2 Pro accepts 1,000,000 input tokens.
Which one generates tokens faster?
Kimi K3 at 73.1 tok/s and MiMo V2 Pro at 41.3 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; MiMo V2 Pro accepts text, image, video and audio input and supports web search.
Can I call Kimi K3 and MiMo V2 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.
AIHubMix