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 /M
Output$15 /M
Cache read$0.3 /M
← ModelsKimi K3Sf Kimi K2 Thinking
Kimi K3 vs Sf Kimi K2 Thinking
Compare Kimi K3 from Moonshot AI and Sf Kimi K2 Thinking 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.
Kimi K3Sf Kimi K2 Thinking+ Add model · 2/4
Sf Kimi K2 Thinking
Moonshot AI · → text
Input$0.548 /M
Output$2.192 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
Sf Kimi K2 Thinking
Input /M
$3
$0.548
Output /M
$15
$2.192
Cache read /M
$0.3
-
Context length
1,048,576
256,000
Max output
1,048,576
0
Time to First Token
0.9 s
1.6 s
Throughput
73.1 tok/s
42.4 tok/s
Modalities
textimagevideo
Supported Parameters
thinkingfunction callingstructured outputs
API Formats
Released
July 16, 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-k3sf-kimi-k2-thinking
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3sf-kimi-k2-thinking
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3sf-kimi-k2-thinking
1360142014801540
Overall
14181486
Coding
14671531
Math
14161416
Hard prompts
14371505
Instruction following
13901479
Multi-turn
14041499
Creative writing
13821470
Longer query
14031502
Chinese
14541527
English
14231491
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.
Sf Kimi K2 Thinking
$65.76 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, Sf Kimi K2 Thinking?
Sf Kimi K2 Thinking: $2.192/M output tokens; Kimi K3: $15/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
Kimi K3: 1531; Sf Kimi K2 Thinking: 1467 (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 Sf Kimi K2 Thinking accepts 256,000 input tokens.
Which one generates tokens faster?
Kimi K3 at 73.1 tok/s and Sf Kimi K2 Thinking at 42.4 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
Can I call Kimi K3 and Sf Kimi K2 Thinking 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.
