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
Qwen3 Max
Kimi K3 vs Qwen3 Max
Output tokens cost $15.00 per million on Kimi K3 and $1.80 per million on Qwen3 Max. Input tokens cost $3.00 per million on Kimi K3 and $0.45 per million on Qwen3 Max. Cached input tokens are billed at $0.30 per million on Kimi K3 and $0.09 per million on Qwen3 Max. Context lengths are 1,048,576 tokens on Kimi K3 and 262,144 tokens on Qwen3 Max. Time to first token (TTFT) measured on AIHubMix is 0.9s on Kimi K3 and 1.3s on Qwen3 Max. Measured output throughput is 73.1 tok/s on Kimi K3 and 46.0 tok/s on Qwen3 Max. On the LMArena coding leaderboard Kimi K3 scores 1531 and Qwen3 Max scores 1475.
Kimi K3Qwen3 Max+ Add model · 2/4
Qwen3 Max
Qwen · text, image → text
The Tongyi Qianwen 3 series Max model has undergone special upgrades in intelligent agent programming and tool invocation compared to the preview version. The officially released model this time reaches SOTA level in the field and is adapted to more complex intelligent agent scenarios.
Input$0.45 /M
Output$1.80 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Kimi K3
Qwen3 Max
Input /M
$3.00
$0.45
Output /M
$15.00
$1.80
Cache read /M
$0.30
$0.09
Context length
1,048,576
262,144
Max output
1,048,576
65,536
Time to First Token
0.9 s
1.3 s
Throughput
73.1 tok/s
46.0 tok/s
Modalities
textimagevideo
textimage
Supported Parameters
thinkingfunction callingstructured outputs
toolsfunction 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-k3qwen3-max
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
kimi-k3qwen3-max
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
kimi-k3qwen3-max
1360142014801540
Overall
14241486
Coding
14751531
Math
14301430
Hard prompts
14481505
Instruction following
14161479
Multi-turn
14501499
Creative writing
13941470
Longer query
14331502
Chinese
14401527
English
14341491
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.
Qwen3 Max
$54.10 /mo
Kimi K3
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Kimi K3, Qwen3 Max?
Qwen3 Max: $1.80/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; Qwen3 Max: 1475 (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 Qwen3 Max accepts 262,144 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 65,536 tokens on Qwen3 Max.
Which one generates tokens faster?
Kimi K3 at 73.1 tok/s and Qwen3 Max at 46.0 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; Qwen3 Max accepts text and image input and supports tool calling, function calling and structured outputs.
Can I call Kimi K3 and Qwen3 Max 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