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
MiniMax M2.1
Kimi K3 vs MiniMax M2.1
Output tokens cost $15.00 per million on Kimi K3 and $1.15 per million on MiniMax M2.1. Input tokens cost $3.00 per million on Kimi K3 and $0.29 per million on MiniMax M2.1. Cached input tokens are billed at $0.30 per million on Kimi K3 and $0.29 per million on MiniMax M2.1. Context lengths are 1,048,576 tokens on Kimi K3 and 204,800 tokens on MiniMax M2.1. Time to first token (TTFT) measured on AIHubMix is 0.9s on Kimi K3 and 0.6s on MiniMax M2.1. Measured output throughput is 73.1 tok/s on Kimi K3 and 87.6 tok/s on MiniMax M2.1. On the LMArena coding leaderboard Kimi K3 scores 1531 and MiniMax M2.1 scores 1439.
Kimi K3MiniMax M2.1+ Add model · 2/4
MiniMax M2.1
Minimax · text → text
MiniMax-M2.1 redefines efficiency for intelligent agents. It is a compact, fast, and cost-effective MoE model with a total of 230 billion parameters and 10 billion active parameters, designed for top performance in coding and intelligent agent tasks while maintaining strong general intelligence. With only 10 billion active parameters, MiniMax-M2 delivers the complex end-to-end tool usage performance expected from today's leading models, but in a more streamlined form factor, making deployment and scaling easier than ever before.
Input$0.29 /M
Output$1.15 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
MiniMax M2.1
Input /M
$3.00
$0.29
Output /M
$15.00
$1.15
Cache read /M
$0.30
$0.29
Context length
1,048,576
204,800
Max output
1,048,576
192,000
Time to First Token
0.9 s
0.6 s
Throughput
73.1 tok/s
87.6 tok/s
Modalities
textimagevideo
text
Supported Parameters
thinkingfunction callingstructured outputs
thinkingtoolsfunction callingstructured outputs
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-k3minimax-m2.1
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3minimax-m2.1
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3minimax-m2.1
13201380144015001560
Overall
13851486
Coding
14391531
Math
13931393
Hard prompts
14081505
Instruction following
13861479
Multi-turn
13911499
Creative writing
13461470
Longer query
14101502
Chinese
14151527
English
14021491
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.
MiniMax M2.1
$34.56 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, MiniMax M2.1?
MiniMax M2.1: $1.15/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; MiniMax M2.1: 1439 (LMArena coding leaderboard).
Which responds faster?
MiniMax M2.1: 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 MiniMax M2.1 accepts 204,800 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 192,000 tokens on MiniMax M2.1.
Which one generates tokens faster?
MiniMax M2.1 at 87.6 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; MiniMax M2.1 accepts text input and supports thinking, tool calling, function calling and structured outputs.
Can I call Kimi K3 and MiniMax M2.1 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