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
O3 Mini
Kimi K3 vs O3 Mini
Output tokens cost $15.00 per million on Kimi K3 and $4.40 per million on O3 Mini. Input tokens cost $3.00 per million on Kimi K3 and $1.10 per million on O3 Mini. Cached input tokens are billed at $0.30 per million on Kimi K3 and $0.55 per million on O3 Mini. Context lengths are 1,048,576 tokens on Kimi K3 and 200,000 tokens on O3 Mini. Time to first token (TTFT) measured on AIHubMix is 0.9s on Kimi K3 and 10.9s on O3 Mini. Measured output throughput is 73.1 tok/s on Kimi K3 and 474.2 tok/s on O3 Mini. On the LMArena coding leaderboard Kimi K3 scores 1531 and O3 Mini scores 1416.
Kimi K3O3 Mini+ Add model · 2/4
O3 Mini
OpenAI · text, image → text
OpenAI's latest fast inference model excels at STEAM tasks and offers exceptional cost-effectiveness. Official support for cache hits reduces input prices by half.
Input$1.10 /M
Output$4.40 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
O3 Mini
Input /M
$3.00
$1.10
Output /M
$15.00
$4.40
Cache read /M
$0.30
$0.55
Context length
1,048,576
200,000
Max output
1,048,576
100,000
Time to First Token
0.9 s
10.9 s
Throughput
73.1 tok/s
474.2 tok/s
Modalities
textimagevideo
textimage
Supported Parameters
thinkingfunction callingstructured outputs
thinking
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-k3o3-mini
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3o3-mini
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3o3-mini
1280136014401520
Overall
13481486
Coding
14161531
Math
13821382
Hard prompts
13701505
Instruction following
13431479
Multi-turn
13401499
Creative writing
13011470
Longer query
13581502
Chinese
13611527
English
13631491
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.
O3 Mini
$132 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, O3 Mini?
O3 Mini: $4.40/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; O3 Mini: 1416 (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 O3 Mini accepts 200,000 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 100,000 tokens on O3 Mini.
Which one generates tokens faster?
O3 Mini at 474.2 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; O3 Mini accepts text and image input and supports thinking.
Can I call Kimi K3 and O3 Mini 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