CC Kimi K2 Instruct
Moonshot AI · text → text
For Claude code only
Input$1.10 /M
Output$3.30 /M
← ModelsCC Kimi K2 InstructKimi K3
CC Kimi K2 Instruct vs Kimi K3
Output tokens cost $3.30 per million on CC Kimi K2 Instruct and $15.00 per million on Kimi K3. Input tokens cost $1.10 per million on CC Kimi K2 Instruct and $3.00 per million on Kimi K3. Cached input tokens are billed at $1.10 per million on CC Kimi K2 Instruct and $0.30 per million on Kimi K3. On the LMArena coding leaderboard CC Kimi K2 Instruct scores 1467 and Kimi K3 scores 1531.
CC Kimi K2 InstructKimi K3+ Add model · 2/4
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
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
CC Kimi K2 Instruct
Kimi K3
Input /M
$1.10
$3.00
Output /M
$3.30
$15.00
Cache read /M
$1.10
$0.30
Context length
0
1,048,576
Max output
0
1,048,576
Time to First Token
-
0.9 s
Throughput
-
73.1 tok/s
Modalities
text
textimagevideo
Supported Parameters
toolsfunction callingstructured outputs
thinkingfunction 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.
cc-kimi-k2-instructkimi-k3
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
cc-kimi-k2-instructkimi-k3
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
cc-kimi-k2-instructkimi-k3
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.
CC Kimi K2 Instruct
$116 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: CC Kimi K2 Instruct, Kimi K3?
CC Kimi K2 Instruct: $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; CC Kimi K2 Instruct: 1467 (LMArena coding leaderboard).
What inputs and capabilities does each model support?
CC Kimi K2 Instruct accepts text input and supports tool calling, function calling and structured outputs; Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs.
Can I call CC Kimi K2 Instruct and Kimi K3 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